Business Research Methods

Research Design

Definition
A research design is a blueprint for conducting research project It specifies details of how the project should be conducted Although a broad approach to the problem has already been designed ,research design specifies details (nuts & bolts) of implementation of that approach A good research design ensures that the project is conducted effectively and efficiently It involves six components or tasks

Six Components of a research design

Design the exploratory, descriptive and/or causal phases of the research design Define the information needed Specify the measurement and scaling procedure Construct and pre test a questionnaire or an appropriate form for data collection Specify the sampling process & sample size Develop a plan of data analysis

Classification of research design The research designs may be broadly classified as Exploratory & Conclusive The primary purpose of exploratory research is to provide insights into the problem Conclusive research is conducted to test specific hypotheses and test specific relationships The findings from conclusive research are used as inputs in managerial decision making

Types of conclusive research Conclusive research may either be descriptive or causal

Descriptive Research

Descriptive research is a type of conclusive research that has as its major objective the description of something-usually market characteristics or functions A descriptive design requires a clear specification of the who, what, when, where, why and the way of research Descriptive research can be classified into cross sectional and longitudinal research

Descriptive research Cross sectional designs involves collection of information from a sample of population elements at a single point in time In longitudinal design repeated measurements are taken on a fixed sample

Causal Design Causal research is designed for the primary purpose of obtaining evidence about cause and effect relationships

Difference Between Exploratory and Conclusive Research

Objective Exploratory: To provide insights & understanding Conclusive: To test specific hypothesis & test relationships Characteristics Exploratory: Information needed is defined only loosely Research process is flexible & unstructured Sample is small & non representative Analysis of primary data is qualitative Conclusive :Information needed is clearly defined Research process is formal & structured Sample is large & representative Data analysis is quantitative Findings/Results Exploratory : Tentative Conclusive : Conclusive Outcome Exploratory : Generally followed by further exploratory or conclusive research Conclusive : Findings used as inputs into decision making

Comparison of basic research designs

Exploratory Research (Unaware of Problem) OBJECTIVES Discover ideas and insights CHARACTERISTICS Flexible Versatile Often front end of total research design METHODS Expert Surveys Pilot Surveys Secondary data ( Analyzed qualitatively) Qualitative research Descriptive Research (Aware of Problem) Causal Research (Problem Clearly Defined)

Describe market characteristics Determine cause and effect or functions relationships

Marked by prior formulation of Manipulation of one or more specific hypothesis independent variables Preplanned and structured design Control of mediating variables Secondary data ( Analyzed quantitatively) Surveys Panels Observational and other data Experiments

Degree of Problem Definition

Exploratory Research (Unaware of Problem) Our sales are declining and we dont know why. Would people be interested in our new product idea? Descriptive Research (Aware of Problem) Causal Research (Problem Clearly Defined)

What kind of people are buying Will buyers purchase more of our product? Who buys our our products in a new package? competitors product? Which of two advertising What features do buyers prefer campaigns is more effective? in our product?

Descriptive Research Example

Mens fragrance market -1/3 size of womens fragrance market -But growing at a faster pace -Women buy 80 % of mens fragrances

Identifying Causality
A causal relationship is impossible to prove. Evidence of causality:
1. The appropriate causal order of events x must precede y 2. Concomitant variation--two phenomena vary together 3. An absence of alternative plausible explanations _elimination of other possible causal factors

Causal relationships

Three types of possible relationships SymmetricalTwo variables fluctuate togetherChanges in either variable are not due to changes in other but due to another cause variable Low attendance of youth in martial art clubs and active participation in discotheques & parties is a result of lifestyle preference

 Reciprocal Two variables mutually influence each other Reading an ad. leads a person to buy a product After usage it sensitises the person to notice & read successive ads Asymmetrical Changes in one variable are responsible for changes in another variable Increase in price may lead to fall in sales

 Asymmetrical relationships are of four types depending on nature of variables Stimulus- response Event that results in response from some object Increase in product price may result in fewer sales Property- Disposition Effect of age on attitude with regard to savings Impact of gender on attitude towards social issues Disposition- Behaviour Persons perception about a brand & its purchase Job satisfaction &productivity Property- behaviour Family life style &purchase of goods, Social class &family savings patterns

 Property Enduring nature of a subject which does not depend on circumstances for its activation Family, status, age. gender ,religion Disposition Inclination to respond in a certain way under certain circumstances Attitudes, opinions, values, perceptions, job satisfaction Behaviour Consumption pattern, savings pattern, purchasing pattern ,work performance, Interpersonal acts,

Examples of Exploratory research

Department Store Patronage Project -Review of academic & trade literature to identify relevant demographic & psychographic factors that influence consumer patronage -Interviews with retailing experts to determine trends :new types of outlets ,shifts in consumer patronage patterns (Internet shopping) -Comparative analysis of 5 best & 5 worst stores of the same chain to get some idea of factors that influence store performance -Focus group to determine factors considered important by consumers in store selection

Examples of Descriptive Research

Department Store Patronage Project WhoWho should be considered a patron of a particular department store -Anyone who enters the store -Anyone who purchases from the store -Anyone who purchase at least once a month -Person in the HH responsible for shopping

 What What information should be obtained from the respondents Frequency with which different stores are patronised for specific product categories Evaluation of various stores in terms of salient choice criteria Information pertaining to specific hypotheses to be tested Psychographics & lifestyles, media consumption habits, Demographics

 When When should the information be obtained from the respondents -Before shopping -While shopping - Immediately after shopping -Some time after shopping to allow time for evaluating their shopping experience

 Where Where should the respondents be contacted to obtain required information -In the store -Outside the store but in the mall -In the parking lot -At home

 Why Why are we obtaining information from respondents ? Why is the marketing research project being conducted -improve the image of sponsoring store -Improve patronage and market share -Change the product mix -Develop a suitable promotional campaign -Decide on the location of a new store

 Way In what way are we going to obtain information from the respondents -Observation of respondents behaviour -Personal interviews -Telephone interviews -Mail interviews -Electronic (Email or internet) interviews

More Examples of descriptive research Market studiesWhich describe-size of the market ,buying power of consumers, availability of distributors &consumer profiles Market share studieswhich determine proportion of total sales received by a company & its competiters Sales analysis studieswhich describe sales by geographic regions, product line, type & size of account

 Image studies Which determine consumer perception of the firm & its products Product usage studies which describe consumption patterns Distribution studies which determine traffic flow patterns and number & location of distributors Pricing studies which describe the range & frequency of price changes & probable consumer response to proposed price changes Advertising studies which describe media consumption habits, audience profile for specific TV programmes and magazines

Examples of causal Studies Test Marketing Application of controlled experiment done in limited but carefully selected test marketsmarketing mix variables (independent variables) are varied and sales (dependent variable) are monitored so that an appropriate marketing strategy can be determined

Characteristics of a good research design

Flexibility,Adaptability,Efficiency,Effective ness Minimise bias and maximise accuracy -For Exploratory research the design should be flexible enough to consider different aspects of problem situation For conclusive research design which minimises bias & maximises reliability is appropriate

Research design concepts

Variable: Anything that may assume different numerical or categorical values Dependent Variable: A variable that is to be predicted or explained :weight Independent variable: A variable that is expected to influence the dependent variable: Height Extraneous variable: Independent variables that are not directly linked with the study but may influence dependent variable: If the study wants to test a hypothesis that a relationship exists between academic achievement and self concept of children then academic achievement is dependent and self concept is independent variable. Intelligence may also affect academic achievement but it is not related to studys purpose and hence it is an extraneous variable.

 Control: It is devised to minimise effects of extraneous variables. Confounded relationship: When a dependent variable is affected by an extraneous variable then relation between the dependent & independent variable is confused or confounded by an extraneous variable Hypothesis: A proposition that tentatively explains certain facts or phenomenon and can be empirically tested

 Experiment: A research method in which conditions are controlled so that one or more variables can be manipulated in order to test a hypothesis. To study impact of a sports coach on cricket teams performance an experiment can be conducted Absolute Experiment: If we want to know impact of a sports coach on cricket teams performance it is an absolute experiment Comparative experiment : If we want to know impact of one sports coach on cricket teams performance compared to impact of another sports coach on cricket teams performance it is a comparative experiment Experimental units: Pre specified plots or blocks where various treatments are used are called experimental units

- Experimental group: - The group of subjects exposed to an experimental treatment. - Group of students provided with a sport coach - Control Group : - A group of subjects who are exposed to the control conditions in an experiment, that is they are subjects not exposed to the experimental treatment - Group of students not provided with a sports coach - Treatment: - It refers to conditions to which experimental groups are subjected and control groups are not subjected

Choosing a research design

Various factors help in selection of the research design & its various aspects These are listed below -Degree of formality desired : Informal or Formal depending on immediate objectives: Exploratory studies are conducted for developing guidelines & hypothesis for future research &are informal in nature with loose structure : Conclusive studies are initiated with proper hypothesis & are formal in nature with a proper structure

 Purpose of the study: If the study is being conducted to find out what,when where,who or how much then a descriptive study is best suited: If study aims at finding out why a causal study is suitable: How many employees are leaving ,when they are leaving & such other issues are covered by descriptive studies: For finding why they are leaving a causal study is suitable.

 Method of data collection : Selection of method for data collection can be done based on the study to be conducted :If research has to be done on traffic flow at a particular junction observation method is the best: If consumer perceptions about a new product are to be estimated then questionnaire method is appropriate Control of variables: If certain variables need to be controlled to find out cause & effect relationship Experiments are conducted by manipulating them.

 Time Dimension: Studies could be either cross sectional or longitudinal or both: Cross sectional studies are conducted once while longitudinal studies are repeated over a period of time Scope of the study: Scope of the study could be limited or wide depending on the problem at hand: Scope of exploratory study could be limited Scope of conclusive study could be wide involving selection of statistical sample to represent the entire population

 Research Environment: Field conditions or laboratory conditions :under field conditions research is carried out as it is while in laboratory conditions real life situations are enacted and an artificial environment is created for research. Subjects perception: Effectiveness of a research study varies according to perceptions of subjects under study: If respondents know that research is being carried or they are being observed they may respond differently. One has to be watchful about such changes to ensure effectiveness