STP452Assignment7 - all predictor variables should be...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
STP429: Assignment #7: Multicollinearity, Diagnostics, and Subset Selection Dr. Jennifer Broatch Use the Job Proficiency data found in jobpro.txt to answer the following questions. The data are from Applied Linear Models, 4ed. (1996) by Neter, Kutner, Nachtsheim, and Wasserman. A personnel officer in a governmental agency administered four new developed aptitude tests to each of 25 applicants for entry level clerical positions. For the purpose of the study, all 25 applicants were accepted for a positions irrespective of their test scores. After a probationary period, each applicant was rated for proficiency on the job. The scores for the 4 tests ( X 1 ,X 2 ,X 3 ,X 4 ) and the job proficiency scores are recorded in the file jobpro.txt. Use the following data step to read in the data. data jobpro; title ’Job Proficiency ’; * READ IN THE DATA; infile ’M:. ....JOBPRO.txt’; input y X1 X2 X3 x4; run; 1. Prepare scatterplots and correlation matrix. Also obtain MC diagnostics and comment. 2. Fit a multiple regression containing all 4 variables as first order terms. Does it appear that
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: all predictor variables should be retained? 3. Find the four best subsets according to the to the R 2 a . 4. Since there is relatively little dierence in R 2 a for the four best subsets what other criterion would you use to help in the selection? 5. Using forward stepwise regression, nd the best subset of predictor variables to predict Y. Use .05 to enter and .10 to delete. In the model statement use selection=stepwise slentry=.05 slstay=.10. 6. How does the best subset according to forward stepwise regression compare with the best subset according to #3? Using all the information, what nal model would you suggest? 7. Using the nal model suggested above. Obtain the residuals and plot them against Y and each of the predictor variables. Comment on assumptions. 8. Prepare a Normal Probability Plot and Test for normality. 9. Obtain the partial regression plots and comment. 10. Assess the presence of outliers and inuential observations. Comment. 1...
View Full Document

This note was uploaded on 09/25/2011 for the course STP 452 taught by Professor Yen during the Fall '10 term at ASU.

Ask a homework question - tutors are online