On Sun, 30 Jun 2013, Pindar wrote:
I think that accessors for the various test-statistics and
p-values would be useful like $ar1, $ar2.
We're contemplating a more general way of making "special" model
data available. Watch this space.
Have you already thought about incorporating a 'collapse'
switch?
Which would do what, exactly?
The GMM() function does not support the use of lists right now.
Could this be improved?
Maybe, but it seems this might encourage the over-proliferation of
instruments that produces singular "A" matrices and hence somewhat
indeterminate results.
Allin Cottrell