Building Good Regression Models

1. (50 points) The Excel file Major League Baseball provides data for one season.
   1. Construct and examine the correlation matrix. Is multicollinearity a potential problem?
   2. Suggest an appropriate set of independent variables that predict the number of wins by examining the correlation matrix.
   3. Find the best multiple regression model for predicting the number of wins having only significant independent variables. How good is your model? Does it use the same variables you thought were appropriate in part b?

Regression with Categorical Independent Variables

1. (50 points) For the Excel file Job Satisfaction, develop a regression model for overall satisfaction as a function of years of service and department that has the largest R square. Which department has the highest impact on satisfaction? (Note that the categorical variable department has multiple levels and will require the use of multiple dummy variables.)

Department	Years	Satisfaction
Administrative	16	3
Administrative	2	9
Administrative	14	6
Maintenance	17	8
Maintenance	15	9
Management	1	9
Management	3	8
Management	3	3
Production	16	5
Production	15	4
Production	13	8
Production	3	10
Production	6	4
Production	1	9
Production	3	7
Production	2	8
Production	3	6
Production	2	6
Production	2	8
Production	15	7
Production	5	7
Production	8	8
Production	17	6
Production	15	9
Production	5	3
Quality Control	1	10
Quality Control	11	7
Shipping / Receiving	21	5
Shipping / Receiving	8	4
Shipping / Receiving	32	5
Shipping / Receiving	2	10
Shipping / Receiving	18	8