June 7, 2019

CHAPTER 11

Summarizing Your Data

LEARNING OBJECTIVES

To see an overview of the four types of data analysis performed by market researchers

To understand summarization data analysis, including when to use percentage, average,

mode, and standard deviation

To become acquainted with the summarize function of your XL Data Analyst

To learn how to create effective presentation tables for categorical and metric variable

summarizations

CHAPTER OUTLINE

Types of Data Analysis Used in Marketing Research

Summarizing the Sample

Generalizing the Findings

Finding Meaningful Differences

Identifying Relationships

Summarizing Your Sample Findings

Summarizing Categorical Variables

How to Summarize Categorical Variables with XL Data Analyst

Summarizing Metric Variables

How to Summarize Metric Variables with XL Data Analyst

Flow Chart of Summarization Analysis

KEY TERMS

Average

Central tendency

Data analysis

Dataset

Differences analysis

Frequency distribution

Generalization analysis

Mode

Percentage distribution

Range

Relationship analysis

Standard Deviation

Summarization analysis

Variability

TEACHING SUGGESTIONS

1. Chapter 11 describes descriptive analysis in detail. The four other types of analysis—

summarization, generalization, differences analysis, and relationships analysis—are

described very briefly simply to provide an overview. Each type is described in detail in the

following chapters. For Chapter 11, students only need to know the definitions and basic

purpose of these analysis types. Table 11.1 is a concise summary of the various types of

analysis. Instructors may want to refer to this table and Figure 11.1 which compares various

types of data analysis with respect to complexity and value as a preview of what topics will

be covered in coming classes.

2. Some instructors may consider the descriptions of the measures of central tendency and

variability too elementary. Students with a good statistics course in their backgrounds,

theoretically, should know these concepts. However, many students seem to forget or repress

these concepts, and especially, standard deviation. The descriptions and the computational

examples are intended to help students recover their knowledge of these concepts. Virtually,

no students are required to compute descriptive statistics by hand, and the examples are

useful in helping them to “see” how the computations take place.

3. Measures of skewness and kurtosis are mentioned but not described in detail as marketing

researchers rarely use them, and managers do not understand them. Instructors who want

their students to understand these concepts can provide supplementary reading from statistics

texts or other sources. The current version of the XL Data Analyst does not report these

measures.

4. It is vital that students understand the relationship between a variable’s type of scale and the

appropriate descriptive analysis measure. They are summarized in Table 11.2.It is

recommended that instructors quiz students, or otherwise devote class time to ensuring that

students retain this knowledge that categorical variables should be summarized with

frequencies and percentage distributions while metric variables should be summarized with

averages, standard deviations, and the range.

5. The use of descriptive statistics can be illustrated effectively by using a research report.

Display the questionnaire used in the study, and have students identify the scaling

assumptions and appropriate descriptive statistics for various questions. Then show the tables

in the report that communicate the findings.

6. Instructors who want a different data set (such as a team project dataset) or who want to have

students learn first-hand how to build an XL Data Analyst data set should remind students

that the procedure for inputting their own data into the XL Data Analyst is in the previous

chapter in the section titled, “Data Analyst Case Datasets and Building your own XL Data

Analyst Dataset.” It gives step-by-step instructions for importing a CSV dataset and setting

up the variable descriptions, value codes, and value labels.