The following analyses are based on a dataset with 4 variables, Y, X1,X2 and X3.Note C(P) is a measure of bias in a model (and bias is bad...)The expected value of C(P) is the value of p for a given model.The more C(P) differs from p the more biased the model is.

Model				R2			C(P)
Y=X1				.39			6.2
Y=X2				.10			2.1
Y=X3				.29			5.7
Y=X1				.49			3.1
Y=X2 X3				.39			2.2
Y=X1				.58			6.1
Y=X1 X2 X3			.68			4.0

a) Which model would you pick as the best model?Why? (10)

b) Is there any correlation between the x variables? (5)