MGMT643, Take Home Portion of Final Exam (50 %) due Wednesday, May 9 R.L. Andrews (In Class Final Exam, 4 to 6:50 p.m., Wednesday, May 9) Part 1 For this part you are to use the SPSS file with 200 observations for HBAT data for Hair 6th edition data from the data files page on the Web. a. (5 points) Perform a nonhierarchical cluster analysis on the data for variables X6 through X22 using Quick Cluster procedure in SPSS (K-Means Cluster on the menu) placing the 200 observations into 10 clusters. Based on the results from this analysis do you think that there are data points that should be considered as outliers and excluded from further analysis? If so, identify the points and give a reason for excluding each point. If not, then give a reason for your conclusion. b. (6 points) Evaluate the normality of the data for variables X6 through X22 by each category for X23 - Consider Strategic Alliance that has two categories (0 = No, would not consider and 1 = Yes, would consider). This means evaluating normality for 17•2=34 sets of data. One can use 34 independent tests of H0: This variable’s data for the specified category is normal VERSUS H1: These data are not normal. One can use the results of the 34 independent tests to perform an umbrella test of H0: The data are normally distributed for each of the 34 variable and X23 category combinations VERSUS H1: The data are not normally distributed for at least one of the 34 variable and X23 category combinations. If the umbrella procedure is to reject the null when the conclusion to one or more of the individual tests is to reject the null, then determine the true level for the umbrella test if =.05 is used for each of the 34 individual tests. Next determine what value of should be used for the 34 individual tests so that the =.05 for the umbrella test. Finally tell whether you think that the data are close enough to being normally distributed so that one could have reasonable confidence in the results for performing a MANOVA to test for a significant difference in the centroids (17 variable means) between the two groups for X23. c. (6 points) Perform the MANOVA described above using =.05 and report your conclusion along with support for this conclusion. If you reject the null then identify those variables that you found to have a significant differences in means for the two categories of X23. d. (8 points) Build a discriminant analysis model to predict the category for X23 using the 17 quantitative variables (X6 through X22) as candidates to be included. Tell which variables you included in your best model and give the appropriate measure(s) to describe how well this model predicts the category for these data. Using this model to estimate the probability that the X23 category is “No, would not consider” for a data point with the values X6 = 8, X7 = 3.8, X8 = 5.3, X9 = 5.4, X10 = 4, X11 = 6, X12 = 5.3, X13 = 7, X14 = 6, X15 = 5.2, X16 = 4.3, X17 = 4.5, X18 = 3.9, X19 = 7, X20 = 7, X21 = 7.7 & X22 = 59. e. (10 points) Build a logistic regression model using X23 as the dependent variable using the 17 quantitative variables (X6 through X22) as candidates to be included as independent variables. Tell which variables you included in your best model. Build a second logistic model that would use variables included in the first model and also include X1. Use each model to estimate the probability that the X23 category is “No, would not consider” for a data point with the values above and X1= 3. f. (3 points) You have given three probabilities for the probability that the X23 category is “No, would not consider.” Pick the one you trust most and tell why you chose it. Part 2, (12 points) I am placing a file named 20_survey_questions.sav on the homework web page for the class to be used for this part. The data contain responses to 20 questions. The response to each question has a rating from 1 to 10. This set of questions will be used again for an expanded study. The persons doing the study would like to reduce the number of questions, without deleting a significant portion of the information. You are to examine this data set and make a recommendation to the group. Answer the following questions, realizing that the criteria are not clear cut for answering these questions. Choose your criteria and explain why you chose them and then answer these questions: a. Do you think any questions can be removed because they provide little additional information that can not be found in the other questions? b. How many questions do you recommend deleting? Why? c. Which questions do recommend deleting? Why?