I've encountered the following "feature."   restrict is putting NA into the standard error rather than 0, making it impossible to retrieve the estimated standard errors as a matrix (or anything else).  Is this as intended?  

? matrix s = $stderr
   The statistic you requested is not available

               coefficient   std. error   t-ratio   p-value
  ----------------------------------------------------------
  const          11.7952       0.0159611    739.0     0.0000 ***
  sqft            0.000000    NA             NA      NA     
  sq_sqft         0.000000     0.000000      NA      NA     
  bedrooms        0.000000     0.000000      NA      NA     
  sq_bedrooms     0.000000     0.000000      NA      NA     
  baths           0.000000     0.000000      NA      NA     
  age             0.000000     0.000000      NA      NA     


It happens with the attached dataset.  Since it won't return anything there is no way to use zeromiss or ok to make it usable.

<hansl>
open "br.gdt"
square sqft bedrooms
logs price
list xlist = const sqft sq_sqft bedrooms sq_bedrooms baths age
matrix Rmat = zeros(6,1)~I(6)
matrix r = { 0 ; 0 ; 0 ; 0; 0; 0 }

ols price xlist
restrict --full
    R=Rmat
    q=r
end restrict
matrix s = $stderr
</hansl>
--
Lee Adkins
Professor of Economics
lee.adkins@okstate.edu

learneconometrics.com