There is a further point that emerges when I experiment with dummify
a bit more. The context is that I have a panel dataset with 91 panel
units identified by the variable. However, for testing I have used
smpl id < 10 --restrict
series pwork = pun_mean(&workers, &id)
function pun_mean(series *x, series *id)
What I find is that dummify creates dummy variables for id=2 to
id=91, not just the values id=2 to id=9 present in the sample
supplied to the function. Surely, this cannot be the intention?
in 1.7.6 in the command reference (text format) in the test category I
see the following entries:
but as gretl script commands they should not be translated (marked for
translation) I guess.
Also I see "Leverage" (with capital L), not sure if this is correct.
with 1.7.6rc2 I experience the following minor flaws. The timing of this report is purely coincidental, I'm not a big fan of last-minute fixes without proper testing, so I'm not pushing this to be fixed before 1.7.6.
1) Clicking ok in the dialog window for generating random variables adds the specified variable, but doesn't close the window. Actually I can imagine that this is a feature, not a bug, but just in case it's not...
2) With panel --random-effects estimation the Hausman test of RE vs. FE isn't printed when the test statistic becomes negative. From what I recall of the translated strings, there used to be a warning message instead. I didn't agree with the content of that warning message, but whatever one thinks of those negative statistics, gretl shouldn't just silently ignore them and leave the user wondering why no test output is shown.
3) And finally a related feature request: I think $hausman should not only access the endogeneity tests after tsls, but should also retrieve the Hausman test after --random-effects.