[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: RE: xtgls & heteroskedasticity
I yield on most of these points to specialists,
but on the last draw attention to the FAQ at
> I have a question regarding the xtgls command and
> heteroskedasticity. I
> have seen that several other people have asked similar
> questions, but I
> couldn't find any answers.
> I am estimating a random effects model and I know that you
> can do a LR test
> for heteroskedasticity using xtgls, igls. That's what I have done and
> though I got some output indicating heteroskedasticity, the
> iteration is
> actually never achieved. Does that mean there is a problem
> with my data (I
> have only 69 observations and 8 years) and what does that
> mean for the
> goodness of the LR test?
> Moreover, if I do any xtgls regression, how do I get an r squared /
> adjusted r squared?
* For searches and help try: