research assignment

Chapter 12 Examining Relationships in Quantitative Research 345

MARKETING RESEARCH IN ACTION The Role of Employees in Developing a Customer Satisfaction Program

The plant manager of QualKote Manufacturing is interested in the impact his year-long effort to implement a quality improvement program is having on the satisfaction of his customers. The plant foreman, assembly-line workers, and engineering staff have closely examined their operations to determine which activities have the most impact on prod- uct quality and reliability. Together, the managers and employees have worked to better understand how each particular job affects the final delivered quality of the product as the customer perceives it.

To answer his questions about customer satisfaction, the plant manager conducted an internal survey of plant workers and managers using a 7-point scale (endpoints are 1 = Strongly Disagree and 7 = Strongly Agree). His plans are to get opinions from within the company first and then do a customer survey on similar topics. He has collected com- pleted surveys from 57 employees. The following are examples of the topics that were covered in the questionnaire:

∙ Data from a variety of external sources such as customers, competitors, and suppliers is used in the strategic planning process. Independent variable A10.

∙ Customers are involved in the product quality planning process. Independent variable A12.

∙ Customer requirements and expectations of the company’s products are used in devel- oping strategic plans and goals. Independent variable A17.

∙ There is a systematic process to translate customer requirements into new/improved products. Independent variable A23.

∙ There is a systematic process to accurately determine customers’ requirements and expectations. Independent variable A31.

∙ The company’s product quality program has improved the level of customer satisfac- tion. Dependent variable A36.

∙ The company’s product quality program has improved the likelihood that customers will recommend us. Dependent variable A37.

∙ Gender of the employee responding: Male = 1; Female = 0. Classification variable A40.

A multiple regression was run using SPSS with responses of the 57 employees as input to the model. The dependent variable was A36 and the independent variables were A10, A12, A17, A23, and A31. The output is shown in Exhibits 12.22 and 12.23. There is a database of QualKote employee responses to these questions available in SPSS format at connect.mheducation.com. The database is labeled QualKote MRIA_Essn 3e.sav.

Results indicate a statistically significant relationship between the metric-dependent variable (A36–Satisfaction) and at least some of the five metric independent variables. The R2 for the relationship is 67.0 and it is statistically significant at the .000 level. This suggests that when employees have more favorable perceptions about some aspects of the implementation of the quality improvement program, they also believe the program has improved customer satisfaction.

hai12117_ch12_316-351.indd 345 8/23/16 11:46 AM

346 Part 4 Data Preparation, Analysis, and Reporting the Results

Hands-On Exercise 1. Will the results of this regression model be useful to the QualKote plant manager? If

yes, how? 2. Which independent variables are helpful in predicting A36–Customer Satisfaction? 3. How would the manager interpret the mean values for the variables reported in

Exhibit 12.22? 4. What other regression models might be examined with the questions from this survey?

Exhibit 12.22 QualKote Descriptive Statistics

hai12117_ch12_316-351.indd 346 8/23/16 11:46 AM

Chapter 12 Examining Relationships in Quantitative Research 347

Exhibit 12.23 Multiple Regression of QualKote Satisfaction Variables

hai12117_ch12_316-351.indd 347 8/23/16 11:46 AM

348 Part 4 Data Preparation, Analysis, and Reporting the Results

Summary Understand and evaluate the types of relationships between variables. Relationships between variables can be described in several ways, including presence, direction, strength of association, and type. Presence tells us whether a consis- tent and systematic relationship exists. Direction tells us whether the relationship is positive or negative. Strength of association tells us whether we have a weak or strong relationship, and the type of relationship is usually described as either linear or nonlinear.

Two variables may share a linear relationship, in which changes in one variable are accompanied by some change (not necessarily the same amount of change) in the other variable. As long as the amount of change stays constant over the range of both variables, the relationship is termed linear. Relationships between two variables that change in strength and/or direction as the values of the variables change are referred to as curvilinear.

Explain the concepts of association and covariation. The terms covariation and association refer to the attempt to quantify the strength of the relationship between two variables. Covariation is the amount of change in one vari- able of interest that is consistently related to change in another variable under study. The degree of association is a numerical measure of the strength of the relationship between two variables. Both these terms refer to linear relationships.

Discuss the differences between Pearson correlation and Spearman correlation. Pearson correlation coefficients are a measure of lin- ear association between two variables of interest. The Pearson correlation coefficient is used when both vari- ables are measured on an interval or ratio scale. When one or more variables of interest are measured on an ordinal scale, the Spearman rank order correlation coef- ficient should be used.

Explain the concept of statistical significance versus practical significance. Because some of the procedures involved in determin- ing the statistical significance of a statistical test include

consideration of the sample size, it is possible to have a very low degree of association between two variables show up as statistically significant (i.e., the population parameter is not equal to zero). However, by considering the absolute strength of the relationship in addition to its statistical significance, the researcher is better able to draw the appropriate conclusion about the data and the population from which they were selected.

Understand when and how to use regression analysis. Regression analysis is useful in answering questions about the strength of a linear relationship between a dependent variable and one or more independent vari- ables. The results of a regression analysis indicate the amount of change in the dependent variable that is associated with a one-unit change in the independent variables. In addition, the accuracy of the regression equation can be evaluated by comparing the predicted values of the dependent variable to the actual values of the dependent variable drawn from the sample. When using regression the assumptions should be checked to ensure the results are accurate and not distorted by devi- ations from the assumptions.

Understand the value and application of structural modeling. Structural modeling enables researchers to analyze complex multivariate models. The most appropriate structural modeling method for marketing research appli- cations is partial least squares structural equation model- ing (PLS-SEM). The PLS-SEM method is an extension of ordinary least squares multiple regression and the sta- tistical objective is to maximize the variance explained in the dependent variable(s). The primary advantages of the method are the ability to examine complex structural models with three or more stages, to include constructs/ variables measured with several questions, to analyze data with non-normal distributions, and to obtain solu- tions with smaller sample sizes.

hai12117_ch12_316-351.indd 348 8/23/16 11:46 AM

Chapter 12 Examining Relationships in Quantitative Research 349

Key Terms and Concepts Beta coefficient 333 Bivariate regression analysis 328 Coefficient of determination (r2) 325 Covariation 319 Curvilinear relationship 318 Homoskedasticity 335 Heteroskedasticity 335 Least squares procedure 329 Linear relationship 318 Model F statistic 334 Multicollinearity 338

Multiple regression analysis 333 Normal curve 335 Ordinary least squares 330 Partial least squares (PLS-SEM) 340 Pearson correlation coefficient 322 Regression coefficient 330 Scatter diagram 319 Spearman rank order correlation coefficient 326 Structural Modeling 339 Unexplained variance 329

Review Questions 1. Explain the difference between testing for significant

differences and testing for association. 2. Explain the difference between association and

causation. 3. What is covariation? How does it differ from

correlation?

4. What are the differences between univariate and bi- variate statistical techniques?

5. What is regression analysis? When would you use it? 6. What is the difference between simple regression and

multiple regression?

Discussion Questions 1. Regression and correlation analysis both describe the

strength of linear relationships between variables. Consider the concepts of education and income. Many people would say these two variables are re- lated in a linear fashion. As education increases, in- come usually increases (although not necessarily at the same rate). Can you think of two variables that are related in such a way that their relationship changes over their range of possible values (i.e., in a curvilinear fashion)? How would you analyze the relationship between two such variables?

2. Is it possible to conduct a regression analysis on two variables and obtain a significant regression equation (significant F-ratio), but still have a low r2? What does the r2 statistic measure? How can you have a low r2 yet still get a statistically significant F-ratio for the overall regression equation?

3. The ordinary least squares (OLS) procedure com- monly used in regression produces a line of “best fit” for the data to which it is applied. How would you define best fit in regression analysis? What is there about the procedure that guarantees a best fit to the data? What assumptions about the use of a regression technique are necessary to produce this result?

4. When multiple independent variables are used to predict a dependent variable in multiple regression, multicollinearity among the independent variables is often a concern. What is the main problem caused by high multicollinearity among the independent vari- ables in a multiple regression equation? Can you still achieve a high r2 for your regression equation if mul- ticollinearity is present in your data?

5. EXPERIENCE MARKETING RESEARCH. Choose a retailer that students are likely to patronize

hai12117_ch12_316-351.indd 349 8/23/16 11:46 AM

350 Part 4 Data Preparation, Analysis, and Reporting the Results

and that sells in both catalogs and on the Internet (e.g., Victoria’s Secret). Prepare a questionnaire that com- pares the experience of shopping in the catalog with shopping online. Then ask a sample of students to visit the website, look at the catalogs you have brought to class, and then complete the questionnaire. Enter the data into a software package and assess your finding statistically. Prepare a report that compares catalog and online shopping. Be able to defend your conclusions.

6. SPSS EXERCISE. Choose one or two other stu- dents from your class and form a team. Identify the different retailers from your community where wireless phones, digital recorders/players, TVs, and other electronics products are sold. Team members should divide up and visit all the different stores and describe the products and brands that are sold in each. Also observe the layout in the store, the store personnel, and the type of advertising the store uses. In other words, familiarize yourself with each retailer’s marketing mix. Use your knowledge of the

marketing mix to design a questionnaire. Interview approximately 100 people who are familiar with all the retailers you selected and collect their responses. Analyze the responses using a statistical software package such as SPSS. Prepare a report of your find- ings, including whether the perceptions of each of the stores are similar or different, and particularly whether the differences are statistically or substan- tively different. Present your findings in class and be prepared to defend your conclusions and your use of statistical techniques.

7. SPSS EXERCISE. Santa Fe Grill owners believe their employees are happy working for the restaurant and unlikely to search for another job. Use the Santa Fe Grill employee database and run a bivariate regres- sion analysis between X11–Team Cooperates and X17–Likelihood of Searching for another Job to test this hypothesis. Could this hypothesis be better examined with multiple regression? If yes, execute a multiple regression and explain the results.

hai12117_ch12_316-351.indd 350 8/23/16 11:46 AM