0

I need help with the following question.

enter image description here

I am really lost, so any help/hint would be much appreciated! I am aware that for best fit model, we are looking for higher $R^2_{Adj}$, smaller $MS_{res}$, PRESS (Prediction error sum of squares), AIC (Akaike Information Criterion) and BIC (Bayesian Information Criterion).

mat95
  • 133
  • 3
    It's a shame students are still being given these questions in stats classes. – gung - Reinstate Monica Apr 19 '21 at 19:10
  • The biggest problem I am having is "efficiency". For example, for part (a) we have that Partial F-test = SSres(red) - SSres(full)/p / SSres(full)/(n-k), and so it takes ages to compute the p-value for all the 6 models.Then the same problem comes up again in the next points. Is there a quicker way? – mat95 Apr 23 '21 at 02:29

0 Answers0