Descriptive Research Spending major dollars, expecting major results

THREE TYPES OF RESEARCH DESIGNS Research design is a set of advance decisions that make up the master plan specifying the methods and procedures for collecting and analyzing the needed information.  Exploratory Research  Descriptive research  Causal research

Exploratory Research Designs Provide a “quick-turnaround” from the time of research proposal to research results. Develop background information. Identify an underlying problem, or “disconnect” in the marketing strategy, “clarify problems and hypotheses” Develop a market forecast for expected sales in a geographic market. Provide a qualitative stage prior to an intensive quantitative stage in a larger research project

Descriptive Research Survey research – Customer satisfaction – Advertising tracking – Consumer panels Large scale observational studies In-depth secondary data analysis – P.O.S (scanner-based) purchasing data – Census data analysis

Epidemiology & Longitudinal Designs Cohort analysis: Correlation analysis and statistical inference: Large samples, small correlations become significant.

Trans Fat and Weight Gain Researchers at Harvard Medical School examined data on 41,518 women from the Nurses Health Study, a long-term study of women's health issues. Scientists found that every increase of one percentage point in the portion of calories from trans fats translated to a two-pound weight gain over eight years.

Heart Disease and Fat Intake Methods We prospectively studied 80,082 women who were 34 to 59 years of age and had no known coronary disease, stroke, cancer, hypercholesterolemia, or diabetes in Information on diet was obtained at base line and updated during follow-up by means of validated questionnaires. During 14 years of follow-up, we documented 939 cases of nonfatal myocardial infarction or death from coronary heart disease. Multivariate analyses included age, smoking status, total energy intake, dietary cholesterol intake, percentages of energy obtained from protein and specific types of fat, and other risk factors. Results Each increase of 5 percent of energy intake from saturated fat, as compared with equivalent energy intake from carbohydrates, was associated with a 17 percent increase in the risk of coronary disease (relative risk, 1.17; 95 percent confidence interval, 0.97 to 1.41; P = 0.10).

Research Design Exploratory Research Design Causal Research Conclusive Research Design Cross-Sectional Design Descriptive Research Longitudinal Design A Classification of Market Research Designs Figure 3.4 A Classification of Market Research Designs Figure 3.4 A Classification of Market Research Designs

Segmentation Bases Ages, Income, Occupation--Who are they?) Store choice--Where they shop? What they buy? Attitudes and motivations: Why do they buy what they buy?

What are our customers’ attitudes? What brands do they prefer? What advertisements do they identify with the actors in the ads? What is an advertisement that represents our company’s biggest strength?

Who are the customers? Ages Sex Lifestyles Occupations Education Income levels

Where do they buy? Specialty stores Full-service, conventional department stores Discount department stores Internet

Why do they buy? Motivations! Importance of the brand? Fulfillment of a basic, economic need (price)? Fulfillment of a functional need? Symbolism of the product decision to others?

Descriptive Data Types: Survey research, cross-sectional, “single slice in time” Panel data, longitudinal Scanner data

Time Respondents Cross-section

Statistical Inference The ability to make a generalization concerning a population from a sample statistic. Typical statistical estimates in descriptive research: – Proportions (percents) – Means – Correlations

Sample Surveyed at T 1 Same Sample also Surveyed at T 2 T1T1 T2T2 Cross Sectional Design Longitudinal Design Time Cross Sectional vs. Longitudinal Designs Figure 3.6 Cross Sectional vs. Longitudinal DesignsFigure 3.6 Cross Sectional vs. Longitudinal Designs

Cross Sectional Data File File composed of a sample taken at a single time period

Longitudinal Data File Sample T 1 Sample T 2

Comparing the two Cross Sectional Studies – Frequencies and proportion of sample at time T for variable x – Cross-tabulations – Mean of sample on variable y – Correlation of two variables (x & y) Longitudinal Studies – Change in the mean for variable y – Change in the mean for variable x – Correlations of the change in the two means.

Maidenform PTA History of self-esteem advertising Decision to broaden distribution from conventional department stores to… Currently conducting tracking research (on current customers?) Wants a complete analysis of the current women’s lingerie market to reposition the consistent brand for broader distribution.

Maidenform Survey Design National: 35 Different Markets (MSAs) Survey type: Mall intercept followed by administered interview Sample size: 3,000 interviews Respondent age: Qualifying questions: Women who had purchased 2 or more bras in past year. Length: 3/4 to an hour

Descriptive Research Who? Buyer demographics What? Brands and prices Why? Motivations and styles Where? Stores shopped How? She makes her purchase decision

Survey showed… More lapsed user than current users Neutral perception Not consistent with current “tracking research” Maidenform has a “dowdier” image, “Their mother’s bra” – “Not satisfying their need for variety”

Findings Distinguish between women who cared about how they looked in their bra versus Women who cared how they looked in their clothes while wearing the bra “What’s your lingerie doing for you?”