Problem 9.21

bailsofhay — Nov 25, 2013, 5:58 PM

data=read.table("http://www.stat.lsu.edu/exstweb/statlab/datasets/KNNLData/CH09PR10.txt")
names(data)=c("y","x1","x2","x3","x4")

fit=lm(y~x1+x2+x3+x4, data=data)
fit


Call:
lm(formula = y ~ x1 + x2 + x3 + x4, data = data)

Coefficients:
(Intercept)           x1           x2           x3           x4  
  -124.3818       0.2957       0.0483       1.3060       0.5198

library(DAAG)

Warning: package 'DAAG' was built under R version 3.0.2

Loading required package: lattice

cv=cv.lm(data,fit,25,printit=FALSE)

Warning: 

 As there is >1 explanatory variable, cross-validation
 predicted values for a fold are not a linear function
 of corresponding overall predicted values.  Lines that
 are shown for the different folds are approximate

Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'
Warning: unimplemented pch value '26'

plot of chunk unnamed-chunk-1


press=sum((data$y-cv$cvpred)^2)
press

[1] 519


SSE=sum((data$y-cv$Predicted)^2)
SSE

[1] 336


# SSE is much smaller than PRESS which would indicate that it is assuming there is
# less unexpected error within the model, which would mean the the MSE validity is 
# less accurate at predicting the predictive ability of the model compared to PRESS.