Research Design

Customer Profitability
N Minimum Maximum Mean Std. Dev

Profits 31634

-221

2071

112

272.84

Profitability Comparison Online Status Mean 116.667 N 3854 Std. Dev % of Total N Std. Error

Offline
Online Total

110.786 27780
111.503 31634

271.301
283.665 272.839

87.82
12.18 100.00

1.628
4.569 1.534

Analysis of Variance Sum of Squares df Mean Square F Sig.

Between Groups
Within Groups Total

117039.30

117039.30 1.572 0.210

74439.99

2354685664.97 31632 2354802704.27 31633

Age Group 1 2 3 4 5 6 7

Offline 5.846 54.582 109.942 131.512 140.413 159.926 192.389

Online -6.547 72.728 143.357 162.541 196.958 169.557 188.888

Difference -12.394 18.146 33.415 31.029 56.545 9.630 -3.501

250.000

200.000

150.000

Profits

100.000

Offline Online

50.000

0.000 Age Group -50.000 Age Group 1 2 3 4 5 6

Income 1 2 3 4 5 6 7 8 9

Offline 74.431 94.668 92.237 96.65 99.536 119.95 136.75 154.91 228.55

Online 46.925 30.667 62.567 66.04 64.221 114.67 145.27 173.65 258.79

Difference -27.506 -64.001 -29.670 -30.609 -35.315 -5.280 8.518 18.741 30.241

300 250 200

Profits

Offline 150 100 50 0 1 2 3 4 5 6 7 8 9 Income Groups Online

Pilgrim Bank
Decision
Whether to charge for online facility usage Customer Incentives to promote online Usage

How do you take a decision?

Is the online channel more profitable than offline?

2. Refine into clear, concise, researchable hypothesis

1.Identify &Define the problem

Research Design

3. Identify Data requirements

5. Interpret & Communicate results

4.Identify and perform analysis to test hypothesis

Identify &Define the problem

1.Impact of online channel usage on customer profitability

2. Online adoption causes increased customer profitability

Refine into clear, concise, researchable hypothesis Identify Data requirements

Research Design

3. Customer profitability, online status, demographics

5. There is no difference in Interpret & Communicate profitability?

results

4.Comparison of profitability between online and offline customers

Identify & perform analysis to test hypothesis

Hypothesis for Research

Hypothesis helps in clarifying research Identify the business problem/question Refine the question into clear concise researchable hypothesis Identify data requirements Identify and perform analysis to test hypothesis Develop alternative explanations Interpret and Communicate the results Make Generalizations

Pilgrim Bank
Hypotheses
Customers who adopted online Channel are more profitable than those who did not How do we test this? What is the difference? Is this difference significant? How do we test? What alternative hypothesis? Role of Demographic Variables Missing values

Research Design: Definition

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 research problems.

A Classification of Marketing Research Designs

Research Design Conclusive Research Design Descriptive Research Causal Research

Exploratory Research Design

Cross-Sectional Design
Single CrossSectional Design

Longitudinal Design

Multiple CrossSectional Design

Uncertainty Influences the Type of Research

CAUSAL OR DESCRIPTIVE
COMPLETELY CERTAIN ABSOLUTE AMBIGUITY

EXPLORATORY

16

17

Exploratory Research
Initial research conducted to clarify and define the nature of a problem Does not provide conclusive evidence Subsequent research expected

18

Exploratory & Conclusive Research

Exploratory
Objective: To provide insights and understanding. Information needed is defined only loosely. Research process is flexible and unstructured. Sample is small and nonrepresentative. Analysis of primary data is qualitative. Tentative. Generally followed by further exploratory or conclusive research.

Conclusive
To test specific hypotheses and examine relationships. Information needed is clearly defined. Research process is formal and structured. Sample is large and representative. Data analysis is quantitative.

Characteristics:

Findings/ Results:

Conclusive.
Findings used as input into decision making.

Outcome:

A Comparison of Research Designs

Exploratory
Objective: Discovery of ideas and insights Flexible, versatile

Descriptive
Describe population characteristics or functions

Causal
Determine cause and effect relationships

Characteristics:

Methods:

Marked by the prior Manipulation of formulation of specific one or more hypotheses independent variables Often the front end Preplanned and of total research structured design Control of other design mediating variables Expert surveys Secondary data: Pilot surveys quantitative analysis Experiments Secondary data: Surveys qualitative analysis Panels Qualitative research Observation and other data

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?

21

Uses of Exploratory Research

Formulate a problem or define a problem more precisely Identify alternative courses of action Develop hypotheses

Isolate key variables and relationships for further examination

Gain insights for developing an approach to the problem Establish priorities for further research

Methods of Exploratory Research

Survey of experts
Pilot surveys Secondary data analyzed in a qualitative way

Literature Reviews
Qualitative research

Use of Descriptive Research

To describe the characteristics of relevant groups, such as consumers, salespeople, organizations, or market areas. To estimate the percentage of units in a specified population exhibiting a certain behavior. To determine the perceptions of product characteristics. To determine the degree to which marketing variables are associated. To make specific predictions.

Methods of Descriptive Research

Secondary data analyzed in a quantitative as opposed to a qualitative manner Surveys Panels Observational and other data

Cross-sectional Designs

Involve the collection of information from any given sample of population elements only once. In single cross-sectional designs, there is only one sample of respondents and information is obtained from this sample only once. In multiple cross-sectional designs, there are two or more samples of respondents, and information from each sample is obtained only once. Often, information from different samples is obtained at different times. Cohort analysis consists of a series of surveys conducted at appropriate time intervals, where the cohort serves as the basic unit of analysis. A cohort is a group of respondents who experience the same event within the same time interval.

Consumption of Various Soft Drinks by Various Age Cohorts

Percentage consuming on a typical day Age 1950 1960 62.6 60.7 46.6 40.8 28.8 C1 1969 1979

8-19 20-29 30-39 40-49 50+ C1: C2: C3: C4: cohort cohort cohort cohort

52.9 45.2 33.9 23.2 18.1 born born born born

73.2 76.0 67.7 58.6 50.0 C2 C5: C6: C7: C8:

81.0 75.8 71.4 67.8 51.9 C3 cohort cohort cohort cohort born born born born

C8 C7 C6 C5 C4

prior to 1900 1901-10 1911-20 1921-30

1931-40 1940-49 1950-59 1960-69

Longitudinal Designs

A fixed sample (or samples) of population elements is measured repeatedly on the same variables

A longitudinal design differs from a cross-sectional design in that the sample or samples remain the same over time

Cross-sectional vs. Longitudinal

CrossSectional Design Sample Surveyed at T1

Longitudinal Design

Sample Surveyed at T1

Same Sample also Surveyed at T2

T2

Time

T1

Causal Research
Conducted to identify cause and effect relationships

30

Uses of Casual Research

To understand which variables are the cause (independent variables) and which variables are the effect (dependent variables) of a phenomenon To determine the nature of the relationship between the causal variables and the effect to be predicted METHOD: Experiments

Identifying Causality
Causal relationships are impossible to prove Evidence of causality 1. Appropriate causal order of events 2. Concomitant variation: Two phenomena vary together 3. Absence of alternative plausible explanations
32

Potential Sources of Error in Research Designs

Total Error Random Sampling Error

Non-sampling Error
Response Error Non-response Error

Researcher Error
Surrogate Information Error Measurement Error Population Definition Error Sampling Frame Error Data Analysis Error

Interviewer Error

Respondent Error
Inability Error Unwillingness Error

Respondent Selection Error Questioning Error Recording Error Cheating Error

Errors in Research

The 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. Random sampling error is the variation between the true mean value for the population and the true mean value for the original sample. 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. Nonsampling errors consist of non-response errors and response errors.

Errors in Research

Non-response error arises when some of the respondents included in the sample do not respond. Response error arises when respondents give inaccurate answers or their answers are misrecorded or misanalyzed.

Pilgrim Bank
Decision
Whether to charge for online facility usage Customer Incentives to promote online Usage

How do you take a decision?

Is the online channel more profitable than offline?

Pilgrim Bank
Hypotheses
Customers who adopted online Channel are more profitable than those who did not How do we test this? What is the difference? Is this difference significant? How do we test? What alternative hypothesis? Role of Demographic Variables Missing values