Soren Lorensen wrote:
I’m working on a project that uses a binary choice model on panel data. Since I have panel data and am using MLE, I’m concerned about heteroskedasticity making my estimates inconsistent and biased.
Are you familiar with any statistical packages with pre-built tests for heteroskedasticity in binary choice ML models? If not, is there value in cutting my data into groups over which I guess the error variance might vary and eyeballing residual plots? Have you other suggestions about how I might resolve this concern?
I replied that I wouldn’t worry so much about heteroskedasticity. Breaking up the data into pieces might make sense, but for the purpose of estimating how the coefficients might vary—that is, nonlinearity and interactions.
Soren shot back:
I’m somewhat puzzled however: homoskedasticity is an identifying assumption in estimating a probit model: if we don’t have it all sorts of bad things can happen to our parameter estimates. Do you suggest not worrying about it because the means of dealing with it are so noisy? [I had hoped to test for it using the algorithm suggested by Davidson & MacKinnon (1993) and to correct for it using a multiplicative heteroskedasticity model.]
I recently graduated from undergrad so my concerns stem from very recent study of econometrics (the professors for whom I work at first nearly scoffed at my concern), but could you please describe (or point me to a source / paper) on why we might not be so concerned about heteroskedasticity in maximum likelihood binary choice models?
To which I replied:
If you’re worried you can always check your model fitting using some simulated data. (That’s the sort of thing I always say.)