SPSS and ordinary least squares

Question

I am doing regression and I am using SPSS/PASW. But it doesn't seem to support Ordinary Least Squares, it only has Partial least Squares and 2-stages Least Squares. Any suggestions about what to do?

Answer 1

This link mentions SPSS weighted least squares. I think if you make all the weights equal to 1.0 you've got what you're calling "ordinary" least squares.

Answer 2

SPSS should default to OLS unless you are doing something to make it switch; I think that the problem is that the default is assumed, and not explicitly mentioned.

Answer 3

I agree with Barry - OLS is 'standard' in SPSS/PASW - the least squares method is used in standard linear regressions and in PASW if you select "Analyze>Regression>Linear" that will give you what you are calling OLS.

This is taken from SPSS/PASW's help documents - it does not directly say OLS under standard linear regression, but infers OLS via this document...

"Standard linear regression models assume that errors in the dependent variable are uncorrelated with the independent variable(s). When this is not the case (for example, when relationships between variables are bidirectional), linear regression using ordinary least squares (OLS) no longer provides optimal model estimates. Two-stage least-squares regression uses instrumental variables that are uncorrelated with the error terms to compute estimated values of the problematic predictor(s) (the first stage), and then uses those computed values to estimate a linear regression model of the dependent variable (the second stage). Since the computed values are based on variables that are uncorrelated with the errors, the results of the two-stage model are optimal."