unit 4 summary

Marketing Data Analysis

Marketing research is a systematic process used to identify and solve marketing-related problems and issues. Addressing the research questions or hypotheses, however, requires that the researcher engage in data analysis. We begin our focus on analysis by examining basic analytical procedures, variance and covariance analysis, correlation and regression, and discriminant analysis. Data Analysis Researchers typically conduct a preliminary analysis of the data before conducting in-depth data analysis. Such analysis helps to provide a basic understanding of and insight into the data. In fact, many marketing research projects do not go beyond basic data analysis. Basic analysis helps us understand data distribution and allows us to test for differences or associations between two means or two medians, but what happens if our research involves multiple variables of interest? The standard statistical tests for differences between more than two means are analyses of variance and covariance. Analysis of Variance and Covariance Analysis of variance (ANOVA) and analysis of covariance (ANCOVA) are used to examine the differences in the mean values of the dependent variable associated with the effect of the controlled independent variables. Essentially, ANOVA is used as a test of means for two or more populations. The null hypothesis, typically, is that all means all equal. For example, suppose a researcher was interested in examining whether heavy, medium, light, or non-users of cereals differed in their preference for Cereal A, measured on a nine-point scale. The null hypothesis that the four groups were not different in preference could be tested using ANOVA. If the set of independent variables, however, consisted of both categorical and metric variables, a researcher is likely to employ ANCOVA. For example, ANCOVA is useful if a researcher wanted to examine the preference of product use groups and loyalty groups, taking into account the respondents¡¦ attitudes towards nutrition and the importance they attached to breakfast as a meal. The last two variables can be measured on a Likert scale (metric), but both product use and brand loyalty represent categorical variables. Correlation and Regression Regression analysis is widely used to explain variation in market share, sales, brand preference, and other marketing results. In fact, we are often interested in summarizing the strength of association between two metric variables, as in the following situations: 1. How strongly are sales related to advertising expenditures? 2. Is there an association between market share and the size of the sales force? 3. Are consumers' perceptions of quality related to their perception of prices? The single most commonly used test of association between two metric variables is the Pearson product moment correlation, which demonstrates the strength of the linear relationship between the tested variables. Understanding the product moment correlation is critical in that it acts as the foundation for all correlation testing, including multiple regression techniques. Regression analyses are powerful and flexible procedures to analyze associative relationships between a metric dependent variable and one or more independent variables. Discriminant Analysis Finally, discriminant analysis is a technique for analyzing data for which the criterion or dependent variable is categorical, but the predictors or independent variables are interval in nature. In fact, examples of discriminant analysis abound in marketing research. This technique can be used to answer questions such as: 1. In terms of demographic characteristics, how do customers who exhibit store loyalty differ from those who do not? 2. Do the various market segments differ in their media consumption habits? 3. What are the distinguishing characteristics of consumers who respond to direct mail solicitations?