BRM-NOTES

Module-1

Introduction to Research

Research

Research is an art of scientific investigation. It is also a systematic design, collection, analysis and the reporting the findings and solutions for the marketing problems of a company.

Objectives of research

1.     Promotes better decision making.

2.     Research is the basis for innovation.

3.     It identifies the problem area.

4.     It helps in forecasting, which is very useful for managers.

5.     Research helps in formulation of policies and strategies.

6.     It helps in the development of new products and in understanding the competitive environment.

7.     It helps in the optimal utilization of resources.

8.     It helps in identifying marketing opportunities and constraints.

9.     It helps in evaluating marketing plans.

Types of Business Research

Research may be classified as

1. Pure Research: Pure research is undertaken for the sake of knowledge without any intention to apply it in practice. Pure research is also known as basic or fundamental research. Pure research helps to find the critical factors in a practical problem .Pure research develops many alternative solutions and thus enables us to choose the best solution.

2. Applied Research: Applied research is conducted when decision must be made about a specific real-life problem. It is thus problem oriented and action directed.

Contribution of Applied Research:

1. Applied research can contribute new facts.

2. Applied research can put theory to the test.

3. Applied research study offers an opportunity to test the validity of existing theory.

4. Applied research may aid in conceptual clarification.

5. Applied research may integrate previously existing theories.

3.  Exploratory Research: Exploratory Research is also known as formulative research. It is the first stage of a three stage process of exploration, description and experimentation. Exploratory research is a preliminary study of an unfamiliar problem about which the researcher has little or no Knowledge. It is similar to a doctor’s initial investigation of a patient.  The need for exploratory studies: The exploratory research is necessary to get initial insight into the problems for the purpose of formulating them for more precise investigation and so called as formulative research.

4. Descriptive Research: Descriptive study is a fact finding investigation with adequate Interpretation. It is the simplest type of research. It is more specific than an exploratory study.

This study aims to identify the characteristics of a community. This study employs simple statistical techniques.

5. Causal Research: Causal research (also referred to as explanatory research) is the investigation of (research into) cause-and-effect relationships. In order to determine causality, it is important to observe variation in the variable that is assumed to cause the change in the other variables, and then measure the changes in the other variables

6. Action Research: Action research is either research initiated to solve an immediate problem or a reflective process of progressive problem solving led by individuals working with others in teams or as part of a "community of practice" to improve the way they address issues and solve problems.

7. Conceptual research: it is used by Philosophers & thinkers. It is related to some abstract ideas or theory. Do research to prove or disapprove his hypothesis

8. Historical research: Based on past records & data in order to understand the future trends. No direct observation, research has to depend on the conclusions or inference drawn in the past.

Criteria or Features of good research study

1.     Empirical-Research is based on direct experience or observation by the researcher.

2.     Logical- Research is based on valid procedures and principles.

3.      Cyclical- Research is a cyclical process because it starts with a problem and ends with a problem.

4.     Analytical-Research utilizes proven analytical procedures in gathering the data, whether historical, descriptive, and experimental and case study.

5.      Critical- Research exhibits careful and precise judgment.

6.      Methodical- Research is conducted in a methodical manner without bias using systematic method and procedures.

7.     Replicability- The research design and procedures are replicated or repeated to enable the researcher to arrive at valid and conclusive results.

Marketing Research

Marketing Research is objective i.e. attempts to provide accurate information that reflects a true state of affairs. It should be conducted impartially.

    The emphasis in marketing is on the identification & satisfaction of customer wants & needs.

    The task of marketing research is to assess the information needs & provide management with the relevant, accurate, valid, reliable & current information.

Limitations of marketing research

1.     MR is not an exact science: Results obtained are not very accurate compared to physical science because of so many uncontrollable variables.

2.     Complex in nature: MR carried out on human begins, who have tendency to behave artificially when they know they are being observed

3.     Inexperienced research staff: Subjectivity is an important limitation in MR. Very difficult to verify the results, which is main characteristic of physical science.

4.     Limitations of time: Generally takes a long time to conduct. By the time results are presented market situation may be changed.

5.     Subjectivity: However objective a person, some time researcher might engage in cheating or misrepresentation of facts or sometimes mislead by respondents. Also researcher might draw conclusion based on his past experience.

6.     Time frame: Top management may hold certain pre conceived opinions on the outcome.

7.     Benefits Vs cost: Benefits should out weight the cost

8.     Availability of resources: Financial or human resource

Scientific Research

Scientific Research is one which yields the same results when repeated by different individuals”. Scientific Research Method is one and same in the branches of science, which is used in all the research and used by various scientists. This method attracted all the trained minds

Characteristic of Scientific Research

1.     Validity: Ability of a measuring instrument to measure what it is supposed to. E.g.     Barometer VS questionnaire

2.     Reliability: the result will remain same even when u repeats it n no of times.

Difficulties in applying scientific methods to marketing research

1.     Complexity of the subject: Deals with human beings .Influence of environmental factors & peers

2.     Difficulty of obtaining accurate measurements: Since information obtained are qualitative in nature. Since participants are human beings, Subjectivity invariably creeps in.

3.     Influence of measurement: When respondents realizes that he is being measured, his response & behavior undergoes a change

4.     Difficulty in testing of hypothesis: In MR it is almost impractical to carry out experiments in a controlled way, which will affect the hypothesis being tested. Very difficulty in making accurate predictions

5.     Role of investigators: Organization is clients of researcher. Sometimes investigator tries to fit in results or manipulates the data or does not conduct exhaustive study.

6.     Time pressure: MR must be conducted & completed within a given time. If more time is consumed in conducting the research, competitors might enter and capture the market.

Scientific methods vs. Non scientific methods 

Business Research

Business research involves establishing objectives and gathering relevant information to obtain the answer to a business issue. Or

Business research can be defined as the systematic and objective process of gathering, recording and analyzing data for aid in making business decisions.

Importance of Marketing Research Roles

1.     Marketing research servers two major functions; (i) it provides information for decision making and (ii) develops new knowledge.

2.     The use of information gathered by the marketing research reduces the risks involved in decision making.

3.     It influences decisions such as pricing of the product, scale of advertising, etc.

4.     The information collected directly affects the planning of the product.

5.     Market research is put to substantial use by firms that produce branded products and are in competition with other brands to know and maintain the popularity of their products among consumers.

External organizations for conducting MR

1.     Advertising agencies: the advertising agencies conduct research for their clients. Ad agencies undertake media studies, group research etc. The ad agencies also conduct opinion research, market potential research etc.

2.     Trade associations: Trade associations also conduct MR. For instance, the confederation of engineering industries conducts MR for various engineering products.

3.     Manufacturers: Manufacturers of smaller industries join together and undertake MR for their mutual benefit. Ex: textile companies have the textile manufacturers association, which conducts research on potential for garments made in the country.

4.     Retailers and wholesalers: the retailers have been predominantly concerned with shop location studies, special promotion studies, pricing, retail stores investigation and sales research and so on. Retailers conduct MR less frequently since they are in close proximity to the customers. The wholesalers are interested in conducting MR on retailer’s behavior. They are also interested in learning about the attitudes of the retailers towards inventories, service provided by the wholesalers etc.

5.     Governmental agencies: MR is also carried out by few government agencies. The government departments collect information on subjects such as agricultural market surplus, consumer goods market surplus, price indices, imports and exports, etc. this helps them in formulating policies.

6.     Universities and institutions: Universities and institutions also conduct MR. Ex: the institutes like the IIMs, IIFT engage themselves in doing marketing research for certain corporate entities.

Research process/steps involved in preparing business research plan/ proposal or designing research

The research process is the step-by-step procedure of developing one's research.

1.     Management problem: It is the most important step, because only when a problem has been clearly and accurately identified can a research project be conducted properly. It asks what the decision maker needs to do. Mostly action oriented and Focuses on symptoms.

2.     Defining the research problem: The research problem is a general statement of an issue meriting research. Its nature will suggest appropriate forms for its investigation. Problem definition involves stating the general marketing research problem and identifying its specific components.

3.     Formulating the research Hypothesis: A good hypothesis relates and explains the known facts. It should also predict new facts. It must be stated in such a way that we can test it by experimentation or further observation, or it is of no scientific value. Also, it must stated in a way that would allow us to show if it is incorrect, i.e., it must be "falsifiable."

4.     Developing the research proposals: Research proposal is a specific kind of document written for a specific purpose. Research involves a series of actions and therefore it presents all actions in a systematic and scientific way. In this way, Research proposal is a blue print of the study which simply outlines the steps that researcher will undertake during the conduct of his/her study

5.     Research design formulation: A research design is a framework or blueprint for conducting the marketing research project. It details the procedures necessary for obtaining the required information, and its purpose is to design a study that will test the hypotheses of interest, determine possible answers to the research questions, and provide the information needed for decision making.

6.     Design of data collection methods: Data collection is the process of gathering and measuring information on variables of interest, in an established systematic fashion that enables one to answer stated research questions, test hypotheses, and evaluate outcomes. Generally there are three types of data collection and they are:

1. Surveys

2. Interviews

3. Focus groups  

7.     Sample design: Sampling is a means of selecting a subset of units from a target population for the purpose of collecting information. This information is used to draw inferences about the population as a whole.

8.     Analysis and interpretation of data: Analysis of data is a process of inspecting, cleaning, transforming, and modeling data with the goal of discovering useful information, suggesting conclusions, and supporting decision-making. Data analysis has multiple facets and approaches, encompassing diverse techniques under a variety of names, in different business, science, and social science domains.

9.     Research report: Entire project documented, Report addresses the specific research question identified, describes the approach, research design, data collection & data analysis methods, & major findings. Reports presented in a comprehensible format.

Research Design formulation

It is a frame work or blue print for conducting research. Details the procedure and designs the study to test the hypotheses of interest, determines possible answers to the research question, and information needed for decision making.

It involves following steps

1.     Secondary data analysis (based on secondary research): Essential step in problem definition. Secondary data are data collected for some purpose other than the problem at hand. Primary data are collected for the specific purpose of addressing the research problem. These data includes information made available by business & government sources, commercial MR firms, and computerized databases.

2.      Qualitative research: When information obtain by above methods are not sufficient then they may go for this method. QR is unstructured, exploratory in nature, based on small samples. Popular QT are Focus group, word association, depth interviews, pilot surveys, case studies. All these tasks help the researcher to understand the environmental context of the problem

3.     Methods of collecting quantitative data: it is through survey, observation, and experimentation. Proper selection, training, supervision, & evaluation of field force minimize data collection errors.

4.     Definition of the information needed: the company needs to know the extent of competition, price quality acceptance from the market. In this context, following information required:

1)    Total demand and company sales

2)    Distribution coverage

3)    Market awareness, attitudes and usage

4)    Marketing expenditure

5)    Competitors’ marketing expenditure

5.      Measurement and scaling procedures: Measurement means assigning numbers or other symbols to characteristics of objects according to certain pre-specified rules.  Scaling is an extension of measurement. Scaling involves creating a continuum on which measured objects are located. 

6.     Questionnaire design: a questionnaire is a paper-and-pencil instrument that is administered to the respondents. The usual questions found in questionnaires are closed-ended questions, which are followed by response options. However, there are questionnaires that ask open-ended questions to explore the answers of the respondents.

7.      Sampling process and sample size: Sampling is a means of selecting a subset of units from a target population for the purpose of collecting information. This information is used to draw inferences about the population as a whole.

8.      Plan of data analysis: Analysis of data is a process of inspecting, cleaning, transforming, and modeling data with the goal of discovering useful information, suggesting conclusions, and supporting decision-making. Data analysis has multiple facets and approaches, encompassing diverse techniques under a variety of names, in different business, science, and social science domains.

Management problem vs. Research problem

Management problem	Research problem
1.     Develop the package for new product.	1.     Evaluate the effectiveness of alternative package design.
2.     To select a media for product advertising.	2.     We should conduct an investigation to determine suitable media. Evaluate the impact of the media in terms of research.
3.     Increase the amount of repurchase behavior of the customer.	3.     Assess current amount repeat purchase behavior.
4.     Introduce new product.	4.     Design a test market through which the likely acceptance of new product can be gauged.
5.     Should the price of the brand be increased?	5.     To determine the price elasticity of demand and the impact on sales and profits of various levels of price changes.

************

Module-2

Business Research Design

Research Design

A research design is a framework or blueprint for conducting the marketing research project. It details the procedures necessary for obtaining the information needed to structure or solve marketing research problems.  It specifies the details – the nuts & bolts of implementing that approach.

A Classification of Marketing Research Designs

1.     Exploratory Research

Exploratory Research is also known as formulative research. It is the first stage of a three stage process of exploration, description and experimentation. Exploratory research is a preliminary study of an unfamiliar problem about which the researcher has little or no Knowledge. It is similar to a doctor’s initial investigation of a patient.  The need for exploratory studies: The exploratory research is necessary to get initial insight into the problems for the purpose of formulating them for more precise investigation and so called as formulative research.

Purpose

– The purpose of exploratory research is to gather preliminary information that will help define problems and suggest hypotheses

– To gain familiarity with a phenomenon or acquire new insight into it in order to formulate a more precise problem or develop hypothesis

Methods of Exploratory Research

1.     Secondary resource analysis/ Review/Survey of concerned Literature: When the investigator proceeds on the path of research he has to take advantage of his predecessors. This technique will save time, cash, and effort. This kind of data can be obtained from professional research organizations, websites, newspapers, magazines, journals of the government, etc.

2.     Expert opinion survey /Experience Survey: It is better to interview those individuals who know about the subject. The objectives of such survey are to obtain insight into the relationship between variables and new ideas relating to the research problem. The respondents picked are interviewed by the researcher. The researcher should prepare an interview schedule for the systematic questioning of informants. Thus an experience survey may enable the researcher to define the problem more consciously and help in the formulation of hypothesis.

3.     Focus Groups discussions: The majority of the organizations engaging in the focus groups first screen the candidates to find out who will compose the particular group. Group interaction is the key factor that differentiates focus group interviews from experience survey that are conducted with one respondent at a time. Furthermore it is the key advantage of the focus group over the majority of exploratory techniques. Due to their interactive nature, ideas sometimes drop “out of the blue” in a focus group discussion.

4.     Comprehensive case methods: Analysis of Insight Stimulating Cases: This includes the study of one or a few situations. It is focused on complex situations and problems; this kind of situations occurs when the interrelations of several individuals are important. In this method of Exploratory Research, some units are analyzed; each unit is called Case.

Uses of Exploratory Research

1.     Formulate a problem or define a problem more precisely

2.     Identify alternative courses of action

3.     Develop hypotheses

4.     Isolate key variables and relationships for further examination

5.     Gain insights for developing an approach to the problem

6.     Establish priorities for further research

2.     Conclusive research Design

Conclusive research aims to verify insights and to aid decision makers in selecting a specific course of action. Conclusive research is sometimes called confirmatory research, as it is used to "confirm" a hypothesis.

In this research there are two types:

1.     Descriptive research

2.     Causal research or experimental research

Descriptive Research

Descriptive study is a fact finding investigation with adequate Interpretation. It is the simplest type of research. It is more specific than an exploratory study. This study aims to identify the characteristics of a community. This study employs simple statistical techniques.

Use of Descriptive Research

1.     Objective is to describe something- usually market characteristics or functions.

2.     To describe the characteristics of relevant groups, such as consumers, salespeople, organizations, or market areas.

3.     To estimate the percentage of units in a specified population exhibiting a certain behavior.

4.     To determine the perceptions of product characteristics.

5.     To determine the degree to which marketing variables are associated.

6.     To make specific predictions

Types of Descriptive Research

1.     Cross sectional studies

A cross-sectional study (also known as a cross-sectional analysis, transversal study, prevalence study) is a type of observational study that involves the analysis of data collected from a population, or a representative subset, at one specific point in time—that is, cross-sectional data. Cross-sectional studies are carried out at one time point or over a short period. They are usually conducted to estimate the prevalence of the outcome of interest for a given population, commonly for the purposes of public health planning. Data can also be collected on individual characteristics, including exposure to risk factors, alongside information about the outcome. In this way cross-sectional studies provide a 'snapshot' of the outcome and the characteristics associated with it, at a specific point in time.

Cross-sectional research studies all have the following characteristics:

 Takes place at a single point in time

 Variables are not manipulated by researchers

 Provide information only; do not answer why

2.     Longitudinal studies

A longitudinal survey is a correlational research study that involves repeated observations of the same variables over long periods of time — often many decades. It is a type of observational study. Longitudinal studies are often used in psychology to study developmental trends across the life span, and in sociology to study life events throughout lifetimes or generations. The reason for this is that, unlike cross-sectional studies, in which different individuals with same characteristics are compared, longitudinal studies track the same people, and therefore the differences observed in those people are less likely to be the result of cultural differences across generations.

Difference between Exploratory research and Descriptive research

Exploratory research	Descriptive research
1.     It is concerned with the “why” aspect of consumer behavior i.e., it tries to understand the problem and not measure the result.	1.     It is concerned with the “what”, “when” or “how often” on the consumer behavior
2.     This research does not require large samples.	2.     This needs large samples of respondents.
3.     Sample need not be representing the population.	3.     Sample must be representative of population.
4.     Due to imprecise statement, data collection is not easy	4.     Statement is precise. Therefore data collection is easy
5.     Characteristics of interest to be measured is not clear	5.     Characteristics of interest to be measured is clear
6.     There is no need for a questionnaire for collecting the data.	6.     There should be a properly designed for collecting the data.
7.     Data collection methods are focus group, literature searching and case study.	7.     Use of panel data, longitudinal, cross-sectional studies.

Causal Research

Causal research (also referred to as explanatory and experimental research) is the investigation of (research into) cause-and-effect relationships. In order to determine causality, it is important to observe variation in the variable that is assumed to cause the change in the other variables, and then measure the changes in the other variables.

Uses of Casual Research

1.     To understand which variables are the cause (independent variables) and which variables are the effect (dependent variables) of a phenomenon

2.     To determine the nature of the relationship between the causal variables and the effect to be predicted

Classification of experimental designs

Classified as:

1. Pre experimental design,

2. Quasi-experimental design,

3. True experimental design,

4. Statistical experimental design

1. Pre experimental design

Pre-experimental designs are so named because they follow basic experimental steps but fail to include a control group. In other words, a single group is often studied but no comparison between an equivalent non-treatment group is made.

Pre-experimental designs include:

-case study design

-One group pre-test/post-test design

-static group comparison design (cross-sectional study)

2. Quasi-experimental design

A quasi-experiment is an empirical study used to estimate the causal impact of an intervention on its target population. Quasi-experimental research shares similarities with the traditional experimental design or randomized controlled trial, but they specifically lack the element of random assignment to treatment or control. Instead, quasi-experimental designs typically allow the researcher to control the assignment to the treatment condition, but using some criterion other than random assignment (e.g., an eligibility cutoff mark)

3.     True experimental design,

True experimental design is regarded as the most accurate form of experimental research, in that it tries to prove or disprove a hypothesis mathematically, with statistical analysis.

For some of the physical sciences, such as physics, chemistry and geology, they are standard and commonly used. For social sciences, psychology and biology, they can be a little more difficult to set up. For an experiment to be classed as a true experimental design, it must fit all of the following criteria.

1.     The sample groups must be assigned randomly.

2.     There must be a viable control group.

3.      Only one variable can be manipulated and tested. It is possible to test more than one, but such experiments and their statistical analysis tend to be cumbersome and difficult.

4.      The tested subjects must be randomly assigned to either control or experimental groups

4.     Statistical experimental design

The term Statistical experimental design refers to a plan for assigning experimental units to treatment conditions. A good experimental design serves three purposes.

1.     Causation: It allows the experimenter to make causal inferences about the relationship between independent variables and a dependent variable.

2.     Control: It allows the experimenter to rule out alternative explanations due to the confounding effects of extraneous variables (i.e., variables other than the independent variables).

3.      Variability: It reduces variability within treatment conditions, which makes it easier to detect differences in treatment outcomes.

Types of errors affecting research design

1.     Total error is the variation between the true mean value in the population of the variable of interest and the observed mean value obtained in the marketing research project. 

2.     Random sampling error is the variation between the true mean value for the population and the true mean value for the original sample. It occurs when the sample selected is not representative of population

3.     Non-sampling errors can be attributed to sources other than sampling, and they may be random or nonrandom: including errors in problem definition, approach, scales, questionnaire design, interviewing methods, and data preparation and analysis. Non-sampling errors consist of non-response errors and response errors.

4.     Non-response error arises when some of the respondents included in the sample do not respond. The primary causes of non-response are refusals & not at homes. This will cause the net or resulting sample to be different in size or composition from the original sample.

5.     Response error arises when respondents give inaccurate answers or their answers are misrecorded or misanalyzed. Response errors can be made by researchers, interviewers or respondents.

6.     Errors made by researcher include:

1)    Surrogate information error: Defined as variation b/w the information needed for the MRP & the information sought by the researcher.

2)    Measurement Error: Is the variation b/w the information sought and information generated by the measurement process employed by the researcher.

3)    Population definition error: Is the variation between the actual population relevant to the problem and the population as defined by the researcher.

4)    Data analysis error: Encompasses errors that occur while raw data are transformed into research findings

7.     Response errors made by interviewer

1)    Respondent selection error: Occurs when interviewers select respondents other than those specified by the sampling design

2)    Questioning error: Error made in asking questions or not probing when more information is needed

3)    Recording error: Error due to hearing, interpreting & recording the answer

4)    Cheating error: When interviewer fabricates answer to a part or whole

8.     Errors made by the respondent are:

1)    Inability error: Inability to provide accurate answer because of unfamiliarity, fatigue, boredom, faulty recall, question content, etc

2)    Unwillingness error: Respondent may intentionally misreport their answer

Exploratory & Conclusive Research Differences

A Comparison of Basic Research Designs

***********

Module-3

Data Collection

Data Collection

Data collection is the process of gathering and measuring information on variables of interest, in an established systematic fashion that enables one to answer stated research questions, test hypotheses, and evaluate outcomes.

Primary and Secondary data

A common classification is based upon who collected the data.

Primary data: Data collected by the investigator himself/ herself for a specific purpose.

Examples: Data collected by a student for his/her thesis or research project. (In movies) The hero is directly told by the heroine that he is her “ideal man”.

Secondary data: Data collected by someone else for some other purpose (but being utilized by the investigator for another purpose).

Examples: Census data being used to analyze the impact of education on career choice and earning.

Advantages of Primary data

1.     It is very accurate.

2.     It is most suitable method of data collection

3.     Results are very good.

Disadvantages of Primary data

1.     It takes much time to collect

2.     It is an expensive method

3.     It takes much labor

Advantages of secondary data

1.     Identify the problem

2.     Better define the problem

3.     Develop an approach to the problem

4.     Formulate an appropriate research design (for example, by identifying the key variables)

5.     Answer certain research questions and test some hypotheses

6.     Interpret primary data more insightfully

Disadvantages of secondary data

1.     The relevance & accuracy to the current problem may be limited

2.     The objectives, nature, & methods used may not be appropriate to present situation

3.     May not be completely current data.

Sources of data

Sources of secondary data

1.     Internal secondary data sources: the data generated within the organization in the process of routine business activities, are referred to as internal secondary data. Financial accounts, production, Quality control, and sales records are examples of such data.

2.     External secondary data sources: the data collected by the researcher from the outside the company. This can be divided into four parts:

1.     Census data: it is the most important data among the sources of data.

2.     Individual project report being published

3.     Data collected for sale on commercial basis called syndicated data

4.     Miscellaneous data.

Primary Data collection methods/ sources of primary data

Data collection methods for impact evaluation vary along a continuum. At the one end of this continuum are quantitative methods and at the other end of the continuum are Qualitative methods for data collection.

1.     Observations

Observation is a process of recording the behavior patterns of people, objects, and occurrences without questioning or communicating with them. Observation can take the place in a laboratory setting or in a natural setting. Generally there are two ways to conduct observation, namely non-participative observation and participative observation. The researcher in non-participative observation does not involve in the activities of the people being observed. He or she merely record whatever happens among the people, including their actions and their behavior, and anything worth recording. On the one hand, the researcher in a participative observation involves fully with the people being observed, with the objective of trying to understand the values, motives and practices of those being researched.

2.     Survey

Survey research is often used to assess thoughts, opinions, and feelings. Survey research can be specific and limited, or it can have more global, widespread goals.

The span of time needed to complete the survey brings us to the two different types of surveys: cross-sectional and longitudinal.

1. Cross-Sectional Surveys

Collecting information from the respondents at a single period in time uses the cross-sectional type of survey. Cross-sectional surveys usually utilize questionnaires to ask about a particular topic at one point in time. For instance, a researcher conducted a cross-sectional survey asking teenagers’ views on cigarette smoking as of May 2010. Sometimes, cross-sectional surveys are used to identify the relationship between two variables, as in a comparative study.

2. Longitudinal Surveys

When the researcher attempts to gather information over a period of time or from one point in time up to another, he is doing a longitudinal survey. The aim of longitudinal surveys is to collect data and examine the changes in the data gathered. Longitudinal surveys are used in cohort studies, panel studies and trend studies.

3.     Questionnaires

Typically, a questionnaire is a paper-and-pencil instrument that is administered to the respondents. The usual questions found in questionnaires are closed-ended questions, which are followed by response options. However, there are questionnaires that ask open-ended questions to explore the answers of the respondents.

Questionnaires have been developed over the years. Today, questionnaires are utilized in various survey methods, according to how they are given. These methods include the self-administered, the group-administered, and the household drop-off. Among the three, the self-administered survey method is often used by researchers nowadays. The self-administered questionnaires are widely known as the mail survey method

4.     Interviews

Between the two broad types of surveys, interviews are more personal and probing. Questionnaires do not provide the freedom to ask follow-up questions to explore the answers of the respondents, but interviews do.

An interview includes two persons - the researcher as the interviewer, and the respondent as the interviewee. There are several survey methods that utilize interviews. These are the personal or face-to-face interview, the phone interview, and more recently, the online interview.

5.     Qualitative Techniques of data collection

Data collection approaches for qualitative research usually involves:

1. Direct interaction with individuals on a one to one basis

2. Or direct interaction with individuals in a group setting

Qualitative research data collection methods are time consuming, therefore data is usually collected from a smaller sample than would be the case for quantitative approaches - therefore this makes qualitative research more expensive. The benefits of the qualitative approach is that the information is richer and has a deeper insight into the phenomenon under study.

Measurement and Scaling Technique

Measurement is a process of mapping aspects of a domain onto other aspects of a range according to some rule of correspondence.

Scaling is the assignment of objects to numbers or semantics according to a rule. In scaling, the objects are text statements, usually statements of attitude, opinion, or feeling.

Basic measurement scales techniques

1.     Nominal scale

Nominal Scale is the crudest among all measurement scales but it is also the simplest scale. In this scale the different scores on a measurement simply indicate different categories. The nominal scale does not express any values or relationships between variables. The nominal scale is often referred to as a categorical scale. The assigned numbers have no arithmetic properties and act only as labels. The only statistical operation that can be performed on nominal scales is a frequency count.

2.     Ordinal scale

Ordinal Scale involves the ranking of items along the continuum of the characteristic being scaled. In this scale, the items are classified according to whether they have more or less of a characteristic. The main characteristic of the ordinal scale is that the categories have a logical or ordered relationship. This type of scale permits the measurement of degrees of difference, (i.e. ‘more’ or ‘less’) but not the specific amount of differences (i.e. how much ‘more’ or ‘less’). This scale is very common in marketing, satisfaction and attitudinal research.

3.     Interval scale

Interval Scale is a scale in which the numbers are used to rank attributes such that numerically equal distances on the scale represent equal distance in the characteristic being measured. An interval scale contains all the information of an ordinal scale, but it also one allows to compare the difference/distance between attributes. Interval scales may be either in numeric or semantic formats. The interval scales allow the calculation of averages like Mean, Median and Mode and dispersion like Range and Standard Deviation.

4.     Ratio scale

Ratio Scale is the highest level of measurement scales. This has the properties of an interval scale together with a fixed (absolute) zero point. The absolute zero point allows us to construct a meaningful ratio. Ratio scales permit the researcher to compare both differences in scores and relative magnitude of scores. Examples of ratio scales include weights, lengths and times.

5.     Attitude measurement scale

Attitudes are composed of 1) Beliefs about the subject 2) Emotional feeling (like-dislike) 3) Readiness to respond behaviorally - i.e. buy7."Attitude is defined as the predisposition to respond to an idea or object, and in marketing it relates to the consumers predisposition to respond to a particular product or service".

6.     Likert’s Scale

Likert, is extremely popular for measuring attitudes, because, the method is simple to administer. With the Likert scale, the respondents indicate their own attitudes by checking how strongly they agree or disagree with carefully worded statements that range from very positive to very negative towards the attitudinal object. Respondents generally choose from five alternatives (say strongly agree, agree, neither agree nor disagree, disagree, strongly disagree). A Likert scale may include a number of items or statements.

7.     Semantic Differential Scale

This is a seven point rating scale with end points associated with bipolar labels (such as good and bad, complex and simple) that have semantic meaning. It can be used to find whether a respondent has a positive or negative attitude towards an object. It has been widely used in comparing brands, products and company images. It has also been used to develop advertising and promotion strategies and in a new product development study.

8.     Thurstone scale

Thurstone's method of pair comparisons can be considered a prototype of a normal distribution-based method for scaling-dominance matrices. Even though the theory behind this method is quite complex the algorithm itself is straightforward. A Thurstone scale has a number of statements to which the respondent is asked to agree or disagree.

There are three types of scale that Thurstone described:

 Equal-appearing intervals method

 Successive intervals method

 Paired comparisons method

9.     Multi-Dimensional Scaling

Multidimensional scaling (MDS) is a means of visualizing the level of similarity of individual cases of a dataset. It refers to a set of related ordination techniques used in information visualization, in particular to display the information contained in a distance matrix.

Process of designing questionnaire

There are eight steps involved in the development of a questionnaire:

1. Decide the information required: It should be noted that one does not start by writing questions. The first step is to decide 'what are the things one needs to know from the respondent in order to meet the survey's objectives?' These, as has been indicated in the opening chapter of this textbook, should appear in the research brief and the research proposal.

2. Define the target respondents: At the outset, the researcher must define the population about which he/she wishes to generalize from the sample data to be collected. For example, in marketing research, researchers often have to decide whether they should cover only existing users of the generic product type or whether to also include non-users. Secondly, researchers have to draw up a sampling frame. Thirdly, in designing the questionnaire we must take into account factors such as the age, education, etc. of the target respondents.

3. Choose the method(s) of reaching your target respondents: It may seem strange to be suggesting that the method of reaching the intended respondents should constitute part of the questionnaire design process. However, a moment's reflection is sufficient to conclude that the method of contact will influence not only the questions the researcher is able to ask but the phrasing of those questions. 

4. Decide on question content: Researchers must always be prepared to ask, "Is this question really needed?" The temptation to include questions without critically evaluating their contribution towards the achievement of the research objectives, as they are specified in the research proposal, is surprisingly strong. No question should be included unless the data it gives rise to is directly of use in testing one or more of the hypotheses established during the research design

5. Develop the question wording: Survey questions can be classified into three forms, i.e. closed, open-ended and open response-option questions. So far only the first of these, i.e. closed questions has been discussed. It provides the respondent with an easy method of indicating his answer - he does not have to think about how to articulate his answer.

6. Put questions into a meaningful order and format:

1. Opening questions: it should be easy to answer and not in any way threatening to THE respondents.

2. Question flow: Questions should flow in some kind of psychological order, so that one leads easily and naturally to the next.

3. Question variety: Respondents become bored quickly and restless when asked similar questions for half an hour or so.

7.  Physical appearance of the questionnaire: The physical appearance of a questionnaire can have a significant effect upon both the quantity and quality of marketing data obtained. The quantity of data is a function of the response rate.

8. Pre-test the questionnaire.

The purpose of pre-testing the questionnaire is to determine:

1.     whether the questions as they are worded will achieve the desired results

2.     whether the questions have been placed in the best order

3.     Whether the instructions to interviewers are adequate.

4.     whether the questions are understood by all classes of respondent

Type of Observation methods/ Conducting an Observation study and Data collection

1. Structured - Unstructured Observation;

For structured observation, the researcher specifies in detail what is to be observed and how the measurements are to be recorded, e.g., an auditor performing inventory analysis in a store. It Reduces observation bias & enhance reliability of the data. It is suitable for use in conclusive research.

In unstructured observation, the observer monitors all aspects of the phenomenon that seem relevant to the problem at hand, e.g., observing children playing with new toys. This method is appropriate for exploratory research.

2. Disguised-Undisguised Observation:

In disguised observation, the respondents are unaware that they are being observed.  Disguise may be accomplished by using one-way mirrors, hidden cameras, or inconspicuous mechanical devices.  Observers may be disguised as shoppers or sales clerks.

In undisguised observation, the respondents are aware that they are under observation.

3. Direct- Indirect observation:

In direct observation, the actual behavior or phenomenon of interest is observed.

In indirect observation, the results of consequences of the phenomenon are observed.

4. Human-Mechanical observation:

Most of the studies in marketing research are based on human observation, wherein trained observers are required to observe and record their observation. In some cases, mechanical devices such as eye cameras are used for observation.

A Classification of Survey Methods

1.     Telephonic interviews: are most popular, followed by personal interviews & mail surveys

Telephonic methods:

1)    Traditional telephone interviews: It involves phoning a sample of respondents and asking them a series of questions

2)    Computer assisted telephone interviewing: interviewing from a central location is now more popular. CATI uses a computerized questionnaire administered to respondents over the telephone. The computer checks the responses for appropriateness & consistency. Interviewing time is reduced, data quality is enhanced & the laborious data collection processes are eliminated.

2.     Personal methods:

1)    In home interviews: Respondents are interviewed in persons in their home. It incurs more cost and particularly used  by syndicate firms

2)    Mall- intercept interviews: Mall shoppers are intercepted & bought to test facilities in the malls. Advantage is more efficient for the respondent to come to the interviewer.

3)    Computer assisted personal interviewing: The respondents sits in front of the terminal & answers a questionnaire. CAPI has been used to collect data at shopping malls, product clinics, conferences, and tradeshows.

3.     Mail methods

1)    Mail interview: In traditional mail interview, questionnaires are mailed to preselected potential respondents. A typical mail interview package consists of outgoing envelope, cover letter, questionnaire, return envelope, & possibly an incentive. No verbal interaction b/w the researcher & the respondent.

2)    Mail panels: A large, nationally representative sample of households that has agreed to participate in periodic mail questionnaires, product tests, telephone surveys. Mail panels can be used to obtain information repeatedly from the same respondents

4.     Electronic methods:

1)    Email interviews: A list of e- mail address is obtained. The survey is written within the body of the E mail message & sent to respondents.

2)    Internet interviews: Internet uses hyper text markup language. Respondents may be recruited from potential databases & asked to go to particular location to complete the survey

Qualitative Research

An unstructured, exploratory research methodology based on small samples that provides insight & understanding of the problem setting.

Quantitative Research

A research methodology that seeks to quantify the data & typically, applies some form of statistical analysis.

Quantitative research must be preceded by appropriate qualitative research

Qualitative vs. Quantitative Research

A Classification of Qualitative Research Procedures

1.     Delphi technique: This process where group of experts in the field gathers together. In the Delphi approach, the group members are asked to make individual judgments about a particular subject, say ‘sales forecast’. These judgments are compiled and returned to the group members, so that they can compare previous judgments with those of others.

2.     Focus group: Is an interview conducted by trained moderator in a non structured & natural manner with a small group of respondents.  Main purpose is to gain insights by listening to a group of people from the appropriate target market talk about issues of interest to the researcher.

3.     Depth interviews: An unstructured, direct, personal interview in which a single respondent is probed by a highly skilled interviewer to uncover underlying motivations, beliefs, attitudes & feelings on a topic. Interviewer attempts to follow a rough outline but the order & specific wordings of probing is influenced by the subject’s replies.

4.     Projective Techniques: An unstructured, indirect form of questioning that encourages respondents to project their underlying motivations, beliefs, attitudes or feelings regarding the issues of concern. In projective techniques, respondents are asked to interpret the behavior of others. 

1)    Word Association: in word association, respondents are presented with a list of words, one at a time and asked to respond to each with the first word that comes to mind. 

2)    Completion Techniques: In Sentence completion, respondents are given incomplete sentences and asked to complete them.  Generally, they are asked to use the first word or phrase that comes to mind. In story completion, respondents are given part of a story – enough to direct attention to a particular topic but not to hint at the ending.  They are required to give the conclusion in their own words. 

3)    A Cartoon Test: In cartoon tests, cartoon characters are shown in a specific situation related to the problem. Cartoon tests are simpler to administer and analyze than picture response techniques.

4)    Thematic Appreciation Test (TAT): TAT is a projective technique. It is used to measure the attitude and perception of the individual. Some picture cards are show to respondents.

*************

Module-4

Sampling and Hypothesis

Sample

The objective of marketing research is to obtain information about the characteristics or parameters of a population.

Population: is the aggregate of all the elements that share some common set of a characteristics, & that comprise the universe

Census: a complete enumeration of the elements of a population or study objects.

Sample:  is a subgroup of the population selected for participation in the study. Sample characteristics called statistics, are then used to make inferences about the population parameters.

The Sampling Design Process

   

1.     Define the population: The collection of all units of a specified type in a given region at a particular point or period of time is termed as a population or universe. Thus, one may consider a population of persons, families, farms, cattle in a region or a population of trees or birds in a forest or a population of fish in a tank etc. depending on the nature of data required. The target population should be defined in terms of elements, sampling units, extent, and time.

a)     An element is the object about which or from which the information is desired, e.g., the respondent. 

b)    A sampling unit is an element, or a unit containing the element, that is available for selection at some stage of the sampling process. 

c)     Extent refers to the geographical boundaries.

d)    Time is the time period under consideration. 

2.     Determine the sampling frame: A list of all the sampling units belonging to the population to be studied with their identification particulars or a map showing the boundaries of the sampling units is known as sampling frame. Examples of a frame are a list of farms and a list of suitable area segments like villages in India or counties in the United States. The frame should be up to date and free from errors of omission and duplication of sampling units.

3.     Specify the sampling unit: Elementary units or group of such units which besides being clearly defined, identifiable and observable, are convenient for purpose of sampling are called sampling units. For instance, in a family budget enquiry, usually a family is considered as the sampling unit since it is found to be convenient for sampling and for ascertaining the required information. In a crop survey, a farm or a group of farms owned or operated by a household may be considered as the sampling unit.

4.     Select a sampling technique: Whether to select the sample through non probability or probability sampling. Non – probability sampling: sampling techniques that do not use chance selection procedures. Rather, they rely on the personnel judgment of the researcher. Probability sampling: in which each element of the population has a fixed probabilistic chance of being selected for the sample.

5.     Sample size: it refers to the no of elements to be included in the study. Important qualitative factors in determining the sample size are

a)     the importance of the decision

b)    the nature of the research

c)     the number of variables

d)    the nature of the analysis

e)     sample sizes used in similar studies

f)      incidence rates

g)     completion rates

h)    resource constraints

6.     Execute the sampling process: Execution of sampling process requires a detailed specification of how the sampling design decisions with respect to the population, sampling frame, sampling unit, sampling technique, & sample size are to be implemented.

Types of Sampling

1.     Probability Sampling

A probability sampling method is any method of sampling that utilizes some form of random selection. In order to have a random selection method, one must set up some process or procedure that assures that the different units in selected population have equal probabilities of being chosen.

Types of Probability Sampling include Simple random sampling, systematic sampling, stratified random sampling, cluster sampling

a)    Simple random sampling

A simple random sample is a subset of individuals (a sample) chosen from a larger set (a population). Each individual is chosen randomly and entirely by chance, such that each individual has the same probability of being chosen at any stage during the sampling process, and each subset of k individuals has the same probability of being chosen for the sample as any other subset of k individuals

b)    Systematic sampling

Systematic sampling is a random sampling technique which is frequently chosen by researchers for its simplicity and its periodic quality. Systematic sampling is a statistical method involving the selection of elements from an ordered sampling frame. The most common form of systematic sampling is an equal-probability method. In this approach, progression through the list is treated circularly, with a return to the top once the end of the list is passed. The sampling starts by selecting an element from the list at random and then every kth element in the frame is selected, where k, the sampling interval (sometimes known as the skip): this is calculated as:

K=   where n is the sample size, and N is the population size.

c)     Stratified random sampling,

A method of sampling that involves the division of a population into smaller groups known as strata. In stratified random sampling, the strata are formed based on members' shared attributes or characteristics. A random sample from each stratum is taken in a number proportional to the stratum's size when compared to the population. These subsets of the strata are then pooled to form a random sample.

The main advantage with stratified sampling is how it captures key population characteristics in the sample.

d)    Cluster sampling

Cluster sampling refers to a sampling method that has the following properties.

    The population is divided into N groups, called clusters.

    The researcher randomly selects n clusters to include in the sample.

    The number of observations within each cluster Mi is known, and M = M1 + M2 + M3 + ... + MN-1 + MN.

    Each element of the population can be assigned to one, and only one, cluster.

Two types of cluster sampling methods are:

v One-stage sampling. All of the elements within selected clusters are included in the sample.

v Two-stage sampling. A subset of elements within selected clusters is randomly selected for inclusion in the sample.

2.     Non Probability Sampling

Non-probability sampling is a sampling technique where the samples are gathered in a process that does not give all the individuals in the population equal chances of being selected.

a)    Convenience sampling

Convenience sampling is a non-probability sampling technique where subjects are selected because of their convenient accessibility and proximity to the researcher.

A statistical method of drawing representative data by selecting people because of the ease of their volunteering or selecting units because of their availability or easy access. The advantages of this type of sampling are the availability and the quickness with which data can be gathered. The disadvantages are the risk that the sample might not represent the population as a whole, and it might be biased by volunteers.

b)    Judgmental sampling

Judgmental sampling is a non-probability sampling technique where the researcher selects units to be sampled based on their knowledge and professional judgment.

This type of sampling technique is also known as purposive sampling and authoritative sampling. The process involves nothing but purposely handpicking individuals from the population based on the authorities or the researcher's knowledge and judgment.

c)     Quota sampling

A sampling method of gathering representative data from a group. As opposed to random sampling, quota sampling requires that representative individuals are chosen out of a specific subgroup. For example, a researcher might ask for a sample of 100 females, or 100 individuals between the ages of 20-30.

Step-by-step Quota Sampling

    The first step in non-probability quota sampling is to divide the population into exclusive subgroups.

    Then, the researcher must identify the proportions of these subgroups in the population; this same proportion will be applied in the sampling process.

     Finally, the researcher selects subjects from the various subgroups while taking into consideration the proportions noted in the previous step.

    The final step ensures that the sample is representative of the entire population. It also allows the researcher to study traits and characteristics that are noted for each subgroup.

d)    Snowball sampling

Snowball sampling is a non-probability sampling technique that is used by researchers to identify potential subjects in studies where subjects are hard to locate. To create a snowball sample, there are two steps: (a) trying to identify one or more units in the desired population; and (b)using these units to find further units and so on until the sample size is met.

Errors in sampling

Sampling error is the deviation of the selected sample from the true characteristics, traits, behaviors, qualities or figures of the entire population.

Sample Size and Sampling Error

Given two exactly the same studies, same sampling methods, same population, the study with a larger sample size will have less sampling process error compared to the study with smaller sample size. Keep in mind that as the sample size increases, it approaches the size of the entire population, therefore, it also approaches all the characteristics of the population, thus, decreasing sampling process error.

          

Ways to Eliminate Sampling Error :

There is only one way to eliminate this error. This solution is to eliminate the concept of sample, and to test the entire population.

In most cases this is not possible; consequently, what a researcher must to do is to minimize sampling process error. This can be achieved by a proper and unbiased probability sampling and by using a large sample size.

Non-probability vs. Probability Sampling

Hypothesis

A hypothesis (H) is an unproven statement or proposition about a factor or phenomenon that is of interest to the researcher. It is a tentative statement about relationship between two or more variables as stipulated by the theoretical framework or the analytical model.

Often, a hypothesis is a possible answer to the research question. Hypothesis are declarative and can be tested empirically where as RQ are interrogative. It provides guidelines on what & how data are to be collected & analyzed. (Suggest variables to be included in the research design.)

Types of hypothesis

1.     Simple hypothesis - this predicts the relationship between a single independent variable (IV) and a single dependent variable (DV)

2.     Complex hypothesis - this predicts the relationship between two or more independent variables and two or more dependent variables.

3.      Directional hypotheses: These are usually derived from theory. They may imply that the researcher is intellectually committed to a particular outcome. They specify the expected direction of the relationship between variables i.e. the researcher predicts not only the existence of a relationship but also its nature.

4.     Non-directional hypotheses: Used when there is little or no theory, or when findings of previous studies are contradictory. They may imply impartiality. Do not stipulate the direction of the relationship.

5.     Associative hypotheses: Propose relationships between variables - when one variable changes, the other changes. Do not indicate cause and effect.

6.     Causal hypotheses: Propose a cause and effect interaction between two or more variables. The independent variable is manipulated to cause effect on the dependent variable. The dependent variable is measured to examine the effect created by the independent variable.

7.     Null hypotheses: These are used when the researcher believes there is no relationship between two variables or when there is inadequate theoretical or empirical information to state a research hypothesis Null hypotheses can be:

a)     simple or complex;

b)    Associative or causal.

8.      Alternative hypothesis:  is one in which some difference or effect is expected.  Accepting the alternative hypothesis will lead to changes in opinions or actions. In marketing research, the null hypothesis is formulated in such a way that its rejection leads to the acceptance of the desired conclusion.  The alternative hypothesis represents the conclusion for which evidence is sought.

9.     Analytical hypothesis: here relationship of analytical variable is found. Used when one would like to specify the relationship between changes in one property leading to change in another. E.g. Income level related to life style. Literacy related to number of children in the family

10.            Statistical hypothesis: these are got from the samples that are measurable. There are 2 types

a.      Hypothesis which indicates difference

b.     Hypothesis which indicates association

11.            Common sense hypothesis: based on what is being observed. E.g. junior students are more disciplined than seniors.

Characteristics of a hypothesis

1.     Clarity of the concepts: concepts should not be abstract. If concepts are not clear, precise problem formulation will be difficult. Different people hold diff concepts about the same object also same word may have several meaning. E.g. wearing a sunglass represents a lifestyle for student whereas it is a protecting device to a doctor

2.     Ability to test: it should be possible to verify the hypothesis. Therefore a good hypothesis is one in which there is empirical evidence. General statement should be avoided. E.g. children of rich parents do not do well in their studies

3.     Specific/ clear: the hypothesis we form should  be specific & clear i.e., the relationship b/w the variables should be clear

4.     Statistical tools: hypothesis should be such that, it is possible to use statistical techniques

5.     Logical: if there are 2 or more hypotheses is derived from the same basic theory, they should not contradict to each other.

6.     Subjectivity: researcher subjectivity or his biased judgment should be eliminated from the hypothesis.

7.     Simple: simple means less constraints or assumptions before formulating it.

8.     Theory: backed up by theoretical framework.

Sources of hypothesis

1.      General Culture: The general pattern of culture helps not only to formulate a hypothesis, but also to guide its trend. The culture has a great influence upon the thinking process of people and hypothesis may be formed to test one or more of these ideas.

2.     Scientific Theory: The knowledge of theory leads to form further generalizations from it. These generalizations form the part of hypothesis.

3.     Analogies: Sometimes a hypothesis is formed from the analogy. A similarity between two phenomena is observed and a hypothesis is formed to test whether the two phenomena are similar in any other respect.

4.     Observation: people’s behavior is observed. In this method we observed behavior to infer the attitudes. This is an indirect method of attitude measurement.

5.     Case studies: case studies published can be used as a source for hypothesis. Normally this is done before the launch of product to find customer taste and preferences.

6.     Past experience: here researcher goes by past experience to formulate the hypothesis.

Formulation of Hypothesis

Hypothesis Formulation

Once having identified research question, it is time to formulate hypothesis. While the research question is broad and includes all the variables one want to consider, the hypothesis is a statement that specific relationship one expect to find from examination of these variables. When formulating the hypothesis (es), there are a few things one need to keep in mind. Good hypotheses meet the following criteria:

1) Identify the independent and dependent variables to be studied.

2) Specify the nature of the relationship that exists between these variables.

3) Simple (often referred to as parsimonious). It is better to be concise than to be long-winded. It is also better to have several simple hypotheses than one complicated hypothesis.

4) Does not include reference to specific measures.

5) Does not refer to specific statistical procedures that will be used in analysis.

6) Implies the population that one is going to study.

7) Is falsifiable and testable.

As indicated above, it is better to have several simple hypotheses than one complex one. However, it is also a good idea to limit the number of hypotheses one use in a study to six or fewer. Studies that address more hypotheses than six will often be too time consuming to keep participants interested, and uninterested participants do not take the importance of their responses as seriously. Another advantage to limiting the number of formal hypotheses one formulate is that too many can make the discussion section of one paper very hard to write.

It is important to remember that one do not have to have a formal hypothesis to justify all comparisons and statistical procedures one might use. For instance, it is only when one starts doing exploratory analysis of one data that one realize that gender is an influencing factor. One does not have to back up and write a hypothesis that addresses this finding. In fact, it is better in most cases to not do this. One can report any statistical findings one feel are relevant, whether or not one have a hypothesis that addressed them.

The final criterion listed above warrants additional mention. A good hypothesis is not only testable, that is, something one can actually test for in one study, but is must also be falsifiable. It is tempting to ignore this requirement, especially as a new researcher. We want so badly to find great things, and for our study to turn out exactly as we expect it to, that we tend to ignore the possibility that we don’t know everything and that no prediction is failsafe when it comes to humans. Try to keep in mind that all research is relevant. Whether or not one finding are what one expect, one will find something. Believe it or not, failing to find group differences can be just as important as finding expected group differences. In fact, studies that return results in opposition to what we were hoping for, or believed would logically occur, often lead to many more great studies than we could have hoped for. After all, it could be great for the findings of one current research to act as a guiding principal to future research… it is likely that this would require less work in terms of literature review, as one would always be familiar with at least a portion of the literature that is relevant to latest study.

Errors in Hypothesis

Type I error: Rejecting the null hypothesis when it is in fact true is called a Type I error. Deciding, before doing a hypothesis test, on a maximum p-value for which they will reject the null hypothesis. This value is often denoted α (alpha) and is also called the significance level. When a hypothesis test results in a p-value that is less than the significance level, the result of the hypothesis test is called statistically significant.

Type II error: Not rejecting the null hypothesis when in fact the alternate hypothesis is true is called a Type II error. (The second example below provides a situation where the concept of Type II error is important.)

Parametric and Non Parametric Test

If the information about the population is completely known by means of its parameters then statistical test is called parametric test E.g.: t- test, f-test, z-test, ANOVA

If there is no knowledge about the population or parameters, but still it is required to test the hypothesis of the population. Then it is called non-parametric test Eg: mann-Whitney, rank sum test, Kruskal-Wallis test

T-Test

A  T-test is any statistical hypothesis test in which the test statistic follows a Student's T distribution if the null hypothesis is supported. It can be used to determine if two sets of data are significantly different from each other, and is most commonly applied when the test statistic would follow a normal distribution if the value of a scaling term in the test statistic were known. When the scaling term is unknown and is replaced by an estimate based on the data, the test statistic (under certain conditions) follows a Student's t distribution.

A two-sample t-test examines whether two samples are different and is commonly used when the variances of two normal distributions are unknown and when an experiment uses a small sample size. For example, a t-test could be used to compare the average floor routine score of the U.S. women's Olympic gymnastics team to the average floor routine score of China's women's team.

The t-test, and any statistical test of this sort, consists of three steps.

1. Define the null and alternate hypotheses,

2. Calculate the t-statistic for the data,

3. Compare tcalc to the tabulated t-value, for the appropriate significance level and degree of freedom. If tcalc > ttab, we reject the null hypothesis and accept the alternate hypothesis.

Otherwise, we accept the null hypothesis.

The t-test can be used to compare a sample mean to an accepted value (a population mean), or it can be used to compare the means of two sample sets.

 t-test to Compare One Sample Mean to an Accepted Value

 t-test to Compare Two Sample Means

T-test to compare One Sample Mean to an Accepted Value

In the example, the mean of arsenic concentration measurements was m=4 ppm, for n=7 and, with sample standard deviation s=0.9 ppm. We established suitable null and alternative hypotheses:

 Null Hypothesis H0: μ = μ0

 Alternate Hypothesis HA: μ > μ0

Where μ0 = 2 ppm is the allowable limit and μ is the population mean of the measured soil (refresher on the difference between sample and population means).

We have already seen how to do the first step, and have null and alternate hypotheses. The second step involves the calculation of the t-statistic for one mean, using the formula:

Where s is the standard deviation of the sample, not the population standard deviation. In our case,

For the third step, we need a table of tabulated t-values for significance level and degrees of freedom, such as the one found in your lab manual or most statistics textbooks. Referring to a table for a 95% confidence limit for a 1-tailed test, we find tν=6,95% = 1.94. (The difference between 1- and 2-tailed distributions was covered in a previous section.)

We are now ready to accept or reject the null hypothesis. If the tcalc > ttab, we reject the null hypothesis. In our case, tcalc=5.88 > ttab=2.45, so we reject the null hypothesis, and say that our sample mean is indeed larger than the accepted limit, and not due to random chance, so we can say that the soil is indeed contaminated.

T-test to compare Two Sample Means

The method for comparing two sample means is very similar. The only two differences are the equation used to compute the t-statistic, and the degrees of freedom for choosing the tabulate t-value. The formula is given by

In this case, we require two separate sample means, standard deviations and sample sizes. The number of degrees of freedom is computed using the formula

And the result is rounded to the nearest whole number. Once these quantities are determined, the same three steps for determining the validity of a hypothesis are used for two sample means.

Z-Test

A Z-test is any statistical test for which the distribution of the test statistic under the null hypothesis can be approximated by a normal distribution. Because of the central limit theorem, many test statistics are approximately normally distributed for large samples. For each significance level, the Z-test has a single critical value (for example, 1.96 for 5% two tailed) which makes it more convenient than the Student's t-test which has separate critical values for each sample size.

Therefore, many statistical tests can be conveniently performed as approximate Z-tests if the sample size is large or the population variance known. If the population variance is unknown (and therefore has to be estimated from the sample itself) and the sample size is not large (n < 30), the Student's t-test may be more appropriate.

If T is a statistic that is approximately normally distributed under the null hypothesis, the next step in performing a Z-test is to estimate the expected value θ of T under the null hypothesis, and then obtain an estimate s of the standard deviation ofT. After that the standard score Z = (T − θ) / s is calculated, from which one-tailed and two-tailed p-values can be calculated as Φ(−Z) (for upper-tailed tests), Φ(Z) (for lower-tailed tests) and 2Φ(−|Z|) (for two-tailed tests) where Φ is the standardnormal cumulative distribution function.

F-Test

The f statistic, also known as an f value, is a random variable that has an F distribution.

An F-test is any statistical test in which the test statistic has an F-distribution under the null hypothesis. It is most often used when comparing statistical models that have been fitted to a data set, in order to identify the model that best fits the population from which the data were sampled. Exact "F-tests" mainly arise when the models have been fitted to the data using least squares. The name was coined by George W. Snedecor, in honour of Sir Ronald A. Fisher. Fisher initially developed the statistic as the variance ratio in the 1920s.

steps required to compute an f statistic:

 Select a random sample of size n1 from a normal population, having a standard deviation equal to σ1.

 Select an independent random sample of size n2 from a normal population, having a standard deviation equal to σ2.

 The f statistic is the ratio of s12/σ12 and s22/σ22.

The following equivalent equations are commonly used to compute an f statistic:

f = [ s12/σ12 ] / [ s22/σ22 ] f = [ s12 * σ22 ] / [ s22 * σ12 ] f = [ Χ21 / v1 ] / [ Χ22 / v2 ] f = [ Χ21 * v2 ] / [ Χ22 * v1 ]

where σ1 is the standard deviation of population 1, s1 is the standard deviation of the sample drawn from population 1, σ2 is the standard deviation of population 2, s2 is the standard deviation of the sample drawn from population 2, Χ21 is the chi-square statistic for the sample drawn from population 1, v1 is the degrees of freedom for Χ21, Χ22 is the chi-square statistic for the sample drawn from population 2, and v2 is the degrees of freedom for Χ22. Note that degrees of freedom v1 = n1 - 1, and degrees of freedom v2 = n2 - 1.

U-Test

The Mann–Whitney U test (also called the Mann–Whitney–Wilcoxon (MWW), Wilcoxon rank-sum test (WRS), or Wilcoxon–Mann–Whitney test) is a nonparametric test of the null hypothesis that two populations are the same against an alternative hypothesis, especially that a particular population tends to have larger values than the other.

It has greater efficiency than the t-test on non-normal distributions, such as a mixture of normal distributions, and it is nearly as efficient as the t-test on normal distributions.

The Wilcoxon rank-sum test is not the same as the Wilcoxon signed-rank test, although both are nonparametric and involve summation of ranks.

A very general formulation is to assume that:

1. All the observations from both groups are independent of each other,

2. The responses are ordinal (i.e. one can at least say, of any two observations, which is the greater),

3. The distributions of both groups are equal under the null hypothesis, so that the probability of an observation from one population (X) exceeding an observation from the second population (Y) equals the probability of an observation from Y exceeding an observation from X. That is, there is a symmetry between populations with respect to probability of random drawing of a larger observation.

4. Under the alternative hypothesis, the probability of an observation from one population (X) exceeding an observation from the second population (Y) (after exclusion of ties) is not equal to 0.5. The alternative may also be stated in terms of a one-sided test, for example: P(X > Y) + 0.5 P(X = Y) > 0.5.

K-W Test/H- test/Rank sum test

The Kruskal–Wallis one-way analysis of variance by ranks (named after William Kruskal and W. Allen Wallis) is a non-parametric method for testing whether samples originate from the same distribution It is used for comparing two or more samples that are independent, and that may have different sample sizes, and extends the Mann–Whitney U test to more than two groups. The parametric equivalent of the Kruskal-Wallis test is the one-way analysis of variance (ANOVA). When rejecting the null hypothesis of the Kruskal-Wallis test, then at least one sample stochastically dominates at least one other sample.

1. Rank all data from all groups together; i.e., rank the data from 1 to N ignoring group membership. Assign any tied values the average of the ranks they would have received had they not been tied.

2. The test statistic is given by:

K= (N-1)

Where:

 is the number of observations in group i

is the rank (among all observations) of observation j from group i

N is the total number of observations across all groups,

 is the average of all the  .

3.    If the data contain no ties the denominator of the expression for K is exactly  and

The last formula only contains the squares of the average ranks.

4. A correction for ties if using the short-cut formula described in the previous point can be made by dividing K by  where G is the number of groupings of different tied ranks, and  is the number of tied values within group i that are tied at a particular value. This correction usually makes little difference in the value of K unless there are a large number of ties.

5. Finally, the p-value is approximated by  If some  values are small (i.e., less than 5) the probability distribution of K can be quite different from this chi-squared distribution. If a table of the chi-squared probability distribution is available, the critical value of chi-squared,

 Can be found by entering the table a tg − 1 degrees of freedom and looking under the desired significance or alpha level.

6. If the statistic is not significant, then there is no evidence of stochastic dominance between the samples. However, if the test is significant then at least one sample stochastically dominates another sample. Therefore, a researcher might use sample contrasts between individual sample pairs, or post hoc tests using Dunn's test, which (1) properly employs the same rankings as the Kruskal-Wallis test, and (2) properly employs the pooled variance implied by the null hypothesis of the Kruskal-Wallis test in order to determine which of the sample pairs are significantly different.[4]When performing multiple sample contrasts or tests, the Type I error rate tends to become inflated, raising concerns about multiple comparisons.

Research report

The Word ‘Report’ is a formal or official statement or just ‘a statement of facts’. A report is a formal document written for a specific audience to meet a specific need it may contain facts of a situation, project, or process, an   analysis &interpretation data, events & record or suggestion & recommendations. A report is a factual & systematic account of a specific business or professional activity.

Types of reports

1.     On the basis of function:-

a.     Analytical report:-An analytical report present data with interpretation & analysis. The report writer’s analysis the facts of a case, Problem, condition, or situation.

b.    Informational report:-Informational report present facts of a case, Problem, Conditional or Situation without any analysis interpretation or recommendations.

2.     On the basis of periodicity:-

a.     Routine report:-As routine report are usually prepared on a periodic basis that is daily weekly fortnightly, monthly & annually.& it is also called periodic report.

b.    Special report: - A specific report is prepared & presented to convey special condition situation problems or occasions.

3.     On the basis of communicative form:-

a.     Oral report: - Oral reports are informal & face- to- face presentation of information. Oral reports are useful for presenting brief information related to routine activities. Projects, developments & so on.

b.    Written report:-Written report is more conventional than oral reports. Most business & technical report use the written mode of presentation because the organizations using this report need to maintain proper for future use & reference. 

4.     On the basis of Nature, scope & length:-

a.     Formal report: - A formal report is usually the result of a thorough investigation of a problem condition or situation it is comparatively longer & need elaborate description & discussion.

b.    Non Formal report:-A Non formal report would be a brief account of a specific business or professional activity. It is usually written to provide introductory information about a routine affair. It is usually short & do not need elaborate description & discussion.

Importance of report writing

1.     Report-writing is an indispensable part of any profession. Almost every important decision in business, industry or government is taken on the basis of information presented or recommendation made in reports.

2.     Every member of the executive staff of an organization is made to write a report at one time or another because without making report no analysis of their work is possible.

3.     Reports keep records which are used if the same situation recurs.

4.     Reports also provide objective recommendations on any problem. Hence the skill of report-writing is as important as good raw material and equipment for running an industry or a business efficiently. An efficient executive need to possess these skills, if he wants to rise up the corporate ladder.

5.     It helps him to perform his functions of planning and evaluating men and material resources efficiently.

Parts or element of a report

A formal report may include the following parts or elements:-

1.     Title page:-.A formal report usually begins with a title page. It contains the title of the report, name of the person or organisation to whom the report is being submitted, the name of report writers & the date.

2.     Preface:-The preface is an optional element in a formal report. It introduces the report by mentioning its salient feature and scope.

3.     Letter of transmittal:-The transmittal letter is a brief is a brief covering letter from the report writer explaining the causes for writing the report. It may contain the objective, Scope & Other highlights of the report.

4.     Acknowledgement:-The Acknowledgement section contains the names of persons who contributed to the production of the report and made the report possible it is just a thank you note.

5.     Table of Contents:-The Table of contents provides the reader an overall view of the report & Shows its Organization.

6.     List of illustrations:-The list of the illustrations gives systematic information about table’s graphs, figures & chats used in the report. It is usually included if the no of these illustrations are more than ten.

7.     Abstract or executive summary:-An abstract or an executive summary summaries the essential information in the report focusing on key facts finding observation result conclusion & recommendations.

8.     Introduction:-This section introduced the reader to the report & prepares them for the discussion that follows by providing background information defining its aims & objectives & discussing the scope& limitations of the report.

9.     Methodology:-While writing a report, information may have to be gathered from library & internet or interviews surveys & formal/ informal discussion. Methodology summarizes the methods of data collection.

10.            Discussion/Description/Analysis:-This is the main part of the report as it presents the data that has collected in an organized form. It focuses on facts & findings.

11.            Conclusion:-This section conveys the significance & meaning of the report to reader by presenting a summary of discussions & finding, result & conclusion.

12.            Recommendations:-This section contains recommendations that are based on result & conclusions.

13.            Appendices:-An Appendix contains supporting material or data, which is kept separate from the main body of the report to avoid interrupting the line of development of the report.

14.            References and bibliography:-This section may contain reference to book, journals, reports, and other sources used in the report. It may also consist of a list of materials for further reference.

Oral vs. Written report

Oral report	Written report
1.     No rigid standard format	1.     Standard format can be applied
2.     Remembering all that is said is difficult	2.     Can be read a no of times & clarification can be sought whenever the reader chooses
3.     Tone, voice modulation, comprehensibility play an imp role	3.     Free from presentation problems
4.     Correcting mistake if any is difficult	4.     Mistakes, if any can be pinpointed & corrected
5.     The audience has no control over the speed of presentation	5.     Has control over speed of reading
6.     Less accurate	6.     Tends to be more accurate
7.     Audience has no choice of picking & choosing from the presentation.	7.     The reader can pick & choose what he thinks is relevant to him

****************

Module-5

Data Analysis

Data for Analysis

Analysis of data is a process of inspecting, cleaning, transforming, and modeling data with the goal of discovering useful information, suggesting conclusions, and supporting decision-making.

Preparing the Data for Analysis

1.     Editing

Editing is the process of checking and adjusting the data for omissions, legibility, and consistency. Editing may be differentiated from coding, which is the assignment of numerical scales or classifying symbols to previously edited data.

The purpose of editing is to ensure the completeness, consistency, and readability of the data to be transferred to data storage. The editor's task is to check for errors and omissions on the questionnaires or other data collection forms.

Types:

1. Field Editing: Preliminary editing by a field supervisor on the same day as the interview to catch technical omissions, check legibility of handwriting, and clarify responses that are logically or conceptually inconsistent.

2. In-house Editing: Editing performed by a central office staff; often dome more rigorously than field editing

•Pitfalls of Editing: Allowing subjectivity to enter into the editing process. Data editors should be intelligent, experienced, and objective. Failing to have a systematic procedure for assessing the questionnaires developed by the research analyst An editor should have clearly defined decision rules to follow.

• Pretesting Edit: Editing during the pretest stage can prove very valuable for improving questionnaire format, identifying poor instructions or inappropriate question wording.

2.     Coding

Coding is translating answers into numerical values or assigning numbers to the various categories of a variable to be used in data analysis. Coding is done by using a code book, code sheet, and a computer card. Coding is done on the basis of the instructions given in the codebook. The code book gives a numerical code for each variable.

Manual processing is employed when qualitative methods are used or when in quantitative studies, a small sample is used, or when the questionnaire/schedule has a large number of open-ended questions, or when accessibility to computers is difficult or inappropriate. However, coding is done in manual processing also. Ex: Male- Code 1,female –Code2

3.     Classification

Distribution of data as a form of classification of scores obtained for the various categories or a particular variable. There are four types of distributions:

a.     Frequency distribution: In social science research, frequency distribution is very common. It presents the frequency of occurrences of certain categories. This distribution appears in two forms: Ungrouped: Here, the scores are not collapsed into categories, e.g., distribution of ages of the students of a BJ (MC) class, each age value (e.g., 18, 19, 20, and so on) will be presented separately in the distribution. Grouped: Here, the scores are collapsed into categories, so that 2 or 3 scores are presented together as a group. For example, in the above age distribution groups like 18-20, 21-22 etc., can be formed)

b.    Percentage distribution: It is also possible to give frequencies not in absolute numbers but in percentages. For instance instead of saying 200 respondents of total 2000 had a monthly income of less than Rs. 500, we can say 10% of the respondents have a monthly income of less than Rs. 500.

c.      Cumulative distribution: It tells how often the value of the random variable is less than or equal to a particular reference value

d.    Statistical distribution: In this type of data distribution, some measure of average is found out of a sample of respondents. Several kind of averages are available (mean, median, mode) and the researcher must decide which is most suitable to his purpose. Once the average has been calculated, the question arises: how representative a figure it is, i.e., how closely the answers are bunched around it.

4.     Tabulation

After editing, which ensures that the information on the schedule is accurate and categorized in a suitable form, the data are put together in some kinds of tables and may also undergo some other forms of statistical analysis. Table can be prepared manually and/or by computers. For a small study of 100 to 200 persons, there may be little point in tabulating by computer since this necessitates putting the data on punched cards. But for a survey analysis involving a large number of respondents and requiring cross tabulation involving more than two variables, hand tabulation will be inappropriate and time consuming.

Tables are useful to the researchers and the readers in three ways: 1. The present an overall view of findings in a simpler way. 2. They identify trends. 3. They display relationships in a comparable way between parts of the findings. By convention, the dependent variable is presented in the rows and the independent variable in the columns.

5.     Validation

Data validation ensures that the survey questionnaires are completed and present consistent data. In this step, should not include the questions that were not answered by most respondents in the data analysis as this would result to bias in the results. However, in the case of incomplete questionnaires, must count the actual number of respondents that were able to answer a particular question. This should be the same for the rest of the questions.

6.     Analysis and Interpretation

The process by which sense and meaning are made of the data gathered in qualitative research, and by which the emergent knowledge is applied to problems.

Types: Descriptive and inferential analysis

Statistical inference is the process of deducing properties of an underlying distribution by analysis of data. Inferential statistical analysis infers properties about a population: this includes testing hypotheses and deriving estimates. The population is assumed to be larger than the observed data set; in other words, the observed data is assumed to be sampled from a larger population.

Inferential statistics can be contrasted with descriptive statistics. Descriptive statistics is solely concerned with properties of the observed data, and does not assume that the data came from a larger population.

Statistical Analysis

Statistical analysis is a component of data analytics. In the context of business intelligence (BI), statistical analysis involves collecting and scrutinizing every single data sample in a set of items from which samples can be drawn.

Bivarate Analysis (Chi-Square only)

Bivariate analysis is one of the simplest forms of quantitative (statistical) analysis. It involves the analysis of two variables (often denoted as X, Y), for the purpose of determining the empirical relationship between them. In order to see if the variables are related to one another, it is common to measure how those two variables simultaneously change together (see also covariance).

Bivariate analysis can be helpful in testing simple hypotheses of association andcausality – checking to what extent it becomes easier to know and predict a value for the dependent variable if we know a case's value of the independent variable.

Chi-Square

A chi-square test, also referred to as  test (infrequently as the chi-squared test), is any statistical hypothesis test in which the sampling distribution of the test statistic is a chi-square distribution when the null hypothesis is true.

To review, the chi-square method of hypothesis testing has seven basic steps

1. State the null and research/alternative hypotheses.

2. Specify the decision rule and the level of statistical significance for the test, i.e., .05, .01, or .001. (A significance level of .01 would mean that the probability of the chi-square value must be .01 or less to reject the null hypothesis, a more stringent criterion than .05.)

3. Compute the expected values.

4. Compute the chi-square statistic.

5. Determine the degrees of freedom for the table. Then identify the critical value of chi-square at the specified level of significance and appropriate degrees of freedom.

6. Compare the computed chi-square statistic with the critical value of chi-square; reject the null hypothesis if the chi-square is equal to or larger than the critical value; accept the null hypothesis if the chi-square is less than the critical value.

7. State a substantive conclusion, i.e., describe the meaning and importance of the test results in terms of the historical problem under investigation.

Multivariate Analysis (Theory Only)

Multivariate Data Analysis refers to any statistical technique used to analyze data that arises from more than one variable. This essentially models reality where each situation, product, or decision involves more than a single variable. The information age has resulted in masses of data in every field. Despite the quantum of data available, the ability to obtain a clear picture of what is going on and make intelligent decisions is a challenge. When available information is stored in database tables containing rows and columns

Multivariate analysis methods typically used for:

 Consumer and market research

 Quality control and quality assurance across a range of industries such as food and beverage, paint, pharmaceuticals, chemicals, energy, telecommunications, etc

 Process optimization and process control

 Research and development

ANOVA: One- Way and Two Way Classification. (Theory Only)

One- Way ANOVA

Analysis of variance (ANOVA) is a collection of statistical models used in order to analyze the differences between group means and their associated procedures (such as "variation" among and between groups), developed by R. A. Fisher. In the ANOVA setting, the observed variance in a particular variable is partitioned into components attributable to different sources of variation. In its simplest form, ANOVA provides a statistical test of whether or not the means of several groups are equal, and therefore generalizes the t-test to more than two groups.

Formula

SSwithin = SStotal - SSamong

 

x = individual observation

r = number of groups

N = total number of observations (all groups)

n = number of observations in group

Steps (assuming three groups)

Create six columns: "x1", "x12", "x2", "x22", "x3", and "x32"

1. Put the raw data, according to group, in "x1", "x2", and "x3"

2. Calculate the sum for group 1.

3. Calculate (Sx) 2 for group 1.

4. Calculate the mean for group 1

5. Calculate Sx2 for group 1.

6. Repeat steps 2-5 for groups 2 and 3

7. Set up SStotal and SSamong formulas and calculate

8. Calculate SSwithin

9. Enter sums of squares into the ANOVA table, and complete the table by calculating: dfamong, dfwithin, MSamong, and MSwithin, and F

10. Check to see if F is statistically significant on probability table with appropriate degrees of freedom and p < .05.

Two Ways ANOVA

The two-way ANOVA is an extension of the one-way ANOVA. The "two-way" comes because each item is classified in two ways, as opposed to one way.

For example, one way classifications might be: gender, political party, religion, or race. Two way classifications might be by gender and political party, gender and race, or religion and race.

Each classification variable is a called a factor and so there are two factors, each having several levels within that factor. The factors are called the "row factor" and the "column factor" because the data is usually arranged into table format. Each combination of a row level and a column level is called a treatment.

Assumptions

1.     The populations from which the samples were obtained must be normally or approximately normally distributed.

2.      The samples must be independent.

3.      The variances of the populations must be equal.

4.     The groups must have the same sample size.

Hypotheses

There are three sets of hypothesis with the two-way ANOVA.

The null hypotheses for each of the sets are given below.

1. The population means of the first factor are equal. This is like the one-way ANOVA for the row factor.

2. The population means of the second factor are equal. This is like the one-way ANOVA for the column factor.

3. There is no interaction between the two factors. This is similar to performing a test for independence with contingency tables.

Two-Way ANOVA Table: It is assumed that main effect A has a levels (and A = a-1 df), main effect B has b levels (and B = b-1 df), n is the sample size of each treatment, and N = abn is the total sample size. Notice the overall degrees of freedom are once again one less than the total sample size.

Source	SS	df	MS	F
Main Effect A	given	A, a-1	SS / df	MS(A) / MS(W)
Main Effect B	given	B,b-1	SS / df	MS(B) / MS(W)
Interaction Effect	given	A*B, (a-1)(b-1)	SS / df	MS(A*B) / MS(W)
Within	given	N - ab, ab(n-1)	SS / df
Total	sum of others	N - 1, abn - 1

Discriminated analysis

1.     Discriminated Analysis (DA), a multivariate statistical  technique is commonly used to build a predictive / descriptive model of group discrimination based on observed predictor variables and to classify each observation into one of the groups.

2.     The common objectives of DA are

i) To investigate differences between groups

ii) To discriminate groups effectively

iii) To identify important discriminating variables

3.     Expressed as D= b0+b1X1+b2X2-----bkXk.

Where D=discriminate score

b’s = discriminate coefficient or weight

X’s= independent variable

4.     E.g. To predict whether patients recovered from a coma or not based on combinations of demographic and treatment variables.

5.     The predictor variables might include age, sex, general health, time between incident and arrival at hospital, various interventions, etc.

6.     In this case the creation of the prediction model would allow a medical practitioner to assess the chance of recovery based on observed variables. The prediction model might also give insight into how the variables interact in predicting recovery.

7.     This analysis helps in

a)     Determination of which independent variable contributes to most of the intergroup differences.

b)    Classification of cases to one of the groups  based on the values of the independent variable

c)     Evaluation of the accuracy of classification

Factor analysis

Factor analysis is a Procedures primarily used for data reduction and summarization. Variables are not classified as either dependent or independent. Instead, the whole set of interdependent relationships among variables is examined in order to define a set of common dimensions called Factors.   

Purpose of Factor Analysis

1.     To identify underlying dimensions called Factors that explain the correlations among a set of variables.

    -- Lifestyle statements may be used to measure the psychographic profile of consumers.

2.     To identify a new, smaller set of uncorrelated variables to replace the original set of correlated variables for subsequent analysis such as Regression or Discriminate Analysis.

      -- Psychographic factors may be used as independent variables to explain the difference between loyal and non loyal customers. 

Assumptions

1.       Models are usually based on linear relationships

2.       Models assume that the data collected are interval scaled

3.       Multicollinearity in the data is desirable because the objective is to identify interrelated set of variables.

4.       The data should be amenable for factor analysis. It should not be such that a variable is only correlated with itself and no correlation exists with any other variables. This is like an Identity Matrix. Factor analysis cannot be done on such data.

Cluster analysis

Cluster analysis aims at grouping observations in clusters

Clusters should possibly be characterized by:

•         High within homogeneity: observations in the same cluster should be similar  (not dissimilar)

•         High between heterogeneity: observations placed in different clusters should be quite distinct (dissimilar)

This means that we are interested in determining groups internally characterized by an high level of cohesion. Also, different clusters should describe different characteristics of the observations

We consider here two different approaches to cluster analysis

Hierarchical (agglomerative) algorithms: Sequential procedures.

At the first step, each observation constitutes a cluster. At each step, the two closest clusters are joined to form a new cluster. Thus, the groups at each step are nested with respect to the groups obtained at the previous step. Once an object has been assigned to a group it is never removed from the group later on in the clustering process.

The hierarchical method produces a complete sequence of cluster solutions beginning with n clusters and ending with one cluster containing all the n observations.

Partitioning algorithms: Iterative procedures

In these methods, the aim is to partition cases into a given number of clusters, say G. The algorithm usually begins with an initial solution (partition). Observations are then reallocated to cluster so as to maximize a pre-specified objective function. Objects possibly change cluster membership throughout the cluster formation process

Conjoint analysis

Conjoint analysis is concerned with the measurement of the joint effect of two or more attributes that are important from the customer’s point of view. In a situation where the company would like to know the most desirable attributes or their combination for new product or service, the use of conjoint analysis is most appropriate.

Ex: an airline would like to know, which is the most desirable combination of attributes to a frequent traveler: 1.Punctuality 2. Air face 3.Quality of food served on the flight 4.Hospitality and empathy shown.

Conjoint analysis is a multivariate technique that captures the exact levels of utility that an individual customer places on various attributes of the product offering. It enables a direct comparison.

There are 3 steps in

1.     Identification of relevant products or service attributes.

2.     Collection of data.

3.     Estimation of worth for the attribute chosen.

Application:

1.     Conjoint analysis is extremely versatile and the range of applications includes virtually in any industry.

2.     New product or service design, including the concepts in the pre-prototyping stage can specifically benefit from the conjoint application.

************

BY

Chandana