[Gretl-devel] source news

Allin Cottrell cottrell at wfu.edu
Tue Jul 21 17:08:16 EDT 2015

On Tue, 21 Jul 2015, Summers, Peter wrote:

> Allin,
> This all looks great. However, when trying out the new 'vif' 
> command, the variance decomposition table is all 0's (both gui and 
> console). This is on Windows 7.
> <hansl>
> open andy.gdt # in POE4
> ols sales const price advert
> vif
> </hansl>

Hmm, not sure what's going wrong there. On Linux with current CVS 
I'm seeing:

Belsley-Kuh-Welsch collinearity diagnostics:

                          --- variance proportions ---
     lambda      cond     const     price    advert
      2.880     1.000     0.001     0.001     0.019
      0.116     4.973     0.010     0.012     0.976
      0.004    26.660     0.989     0.987     0.006

I'll try testing on Windows tomorrow. This seems an unlikely thing 
to work differently across platforms, but maybe the OpenBLAS DLL 
I've built for Windows is somehow wonky? Although in that case I'd 
expect many things to be seriously wrong, not just the BKW 

This is on 64-bit Windows, right?


More information about the Gretl-devel mailing list