Fixed-effects Poisson (Quasi-ML) regression with Robust Standard Errors
xtpqml depvar [indepvars] [if exp] [in range], fe i(varname) irr cluster(varname)]
by ... : may be used with xtpqml; see help by.
Weights are not allowed.
Description
xtpqml is simply a wrapper for the xtpoisson command that computes robust standard errors.
Persons interested in this regression model should also see help xtpoisson, and help poisson.
Options
i(varname) is not optional; it specifies the (numeric) identifier variable for groups in the panel data. This option can be set using iis.
irr reports the estimated coefficients transformed to incident rate ratios, i.e., exp(b) rather than b. Standard errors and confidence intervals are similarly transformed. This option affects how results are displayed, not how they are estimated.
cluster allows for cross-sectional clustering of residuals at a more aggregated level than the individual fixed effect. This is an unusual assumption and users are responsible for providing their own interpretation of the results obtained by specifiying this option
Examples
. xtpqml y x, i(id)
. xtpqml y x, fe i(id)
. xtpqml y x, i(id) irr
. xtpqml y x, i(id) cluster(group)
Also see
Manual: [U] 23 Estimation and post-estimation commands, [XT] xtpoisson