Use backwards elimination to create the “best” model for predicting “Final” star
ID: 3319381 • Letter: U
Question
Use backwards elimination to create the “best” model for predicting “Final” starting with Midterm1, Midterm2, Project, and Homework. Write the final regression equation, the R-squared/Adjusted R-squared and include the final output from your regression. Write a brief summary of your analysis that would be suitable for an email to your boss.
Explanation / Answer
We use Minitab to answer-
Regression Analysis: Final versus Midterm1, Midterm2, Project, Homework
Backward Elimination of Terms
to remove = 0.1
Analysis of Variance
Source DF Adj SS Adj MS F-Value P-Value
Regression 2 25227 12613.7 39.92 0.000
Midterm1 1 7514 7514.2 23.78 0.000
Homework 1 2557 2557.0 8.09 0.006
Error 60 18959 316.0
Total 62 44187
Coefficients
Term Coef SE Coef T-Value P-Value VIF
Constant -0.2 17.5 -0.01 0.993
Midterm1 1.211 0.248 4.88 0.000 1.63
Homework 0.702 0.247 2.84 0.006 1.63
Regression Equation
Final = -0.2 + 1.211 Midterm1 + 0.702 Homework
Fits and Diagnostics for Unusual Observations
Obs Final Fit Resid Std Resid
3 124.00 117.33 6.67 0.41 X
7 98.00 136.17 -38.17 -2.25 R
17 75.00 74.44 0.56 0.04 X
29 78.00 114.26 -36.26 -2.13 R
44 86.00 141.24 -55.24 -3.17 R
56 161.00 138.52 22.48 1.40 X
61 101.00 141.48 -40.48 -2.31 R
R Large residual
X Unusual X
The variable Project And Midterm 2 can be elliminated by Backward ellimination process.
Related Questions
Navigate
Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.