R2 is no nonsense in the context you mention: if you can produce the predicted values from your regression, R2 is the square of the Pearson linear correlation coefficient between predicted and observed values. It is also the ratio of variance in the DV explained by the regression model, relative to total variance in the DV.

Hector

> -----Original Message----- > From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] > On Behalf Of Stephan Golla > Sent: Wednesday, February 23, 2005 4:41 PM > To: SPSSX-L@LISTSERV.UGA.EDU > Subject: SPSS: Time Series Regression with Newey-West standard errors > > > Dear List: > Are there any possibilities in SPSS to run time series > analysis by regression with Newey-West standard errors? I > used stata to calculate the impact of an IV on a DV from > 1997 (quarterly) till 2004. But got a little bit confused by > the stata output. o.k. I know the coefficients. But how can I > calculate the strenght of association and power? Stata did > not provide a R-square. Or is R-square in that context > simply nonsense? Any ideas? Many thanks in advance. Stephan >