[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: A question about modelling heterogenous variances
On Oct 21, 2005, at 9:51 AM, Timothy.Mak@iop.kcl.ac.uk wrote:
This probably exposes my ignorance, but why wouldn't using the robust
option work here? Heteroscedascity adjustments using White's
covariance consistent estimator is what I recommend, which here would
just be -xi: reg age i.sex i.site, robust-. Is there some reason why
that's not appropriate?
Consider the following problem: I want to regress age on sex, but my
dataset was collected from four sites, so I'd like to control for
xi: reg age i.sex i.site
But graphical examination suggests that different sites had different
variances. What's the solution?
* For searches and help try: