[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: Detecting influential cases in count models
My apology in advance if this is a naïve question, but I am new to count models.
Are there techniques for detecting/evaluating influential cases in the negative
binomial regression model (and its zero-inflated counterpart)? If so, is there
anything implemented in Stata? For least squares, I use Cook’s distance and
DFBeta, but after a quick survey of the literature I unable to find comparable
methods for count models. In addition, can anybody recommend an approachable
econometrics text that addresses influential cases for count models?
* For searches and help try: