#3.2
For the model of the previous question, remove all the predictors that are not significant at the 5% level.
(a) Recompute the predictions of the previous question. Are the CIs wider or narrower?
Which predictions would you prefer? Explain.
(b) Test this model against that of the previous question. Which model is preferred?
 
#3.4
Using the sat data
(a) Fit a model with total sat score as the resphonse and expend, ratio and salary as predictors.
Test the hypothesis that b_salary  

(b)

deviance
The deviance is used to compare two models -
in particular in the case of generalized linear models where it has a similar role to residual variance from ANOVA in linear models.