Comparing nested models using F test

Hi all, I want to compare two models to see if they are significantly different.

Total number of obs = 981

Model 1: y = b0 + b1x1 + b2x2 + b3x2
Model 2: y = b0 + b1x1 + b2x2 .... + b5x5

How do I compare the two regressions? Is using the difference in F-values for both models, with df1 = 2, and df2 = 975 (981-6)?


No cake for spunky
It depends what type of regression you are running. Since these are not nested, they have different variables, AIC is probably your best bet. There are chi square tests I believe for analyzing if models are better, but they have to be nested.

This would be a nested model

y=b0 +b1X1 + b2X2

compared to

y=b0 + b1X1

one is a subset of the other.


Ambassador to the humans
We might want to determine if they are nested or not. Seems more likely that they just made a typo on that first model.