xtlogit - Stata
xtlogit - Stata
xtlogit - Stata
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
4 <strong>xtlogit</strong> — Fixed-effects, random-effects, and population-averaged logit models<br />
PA options<br />
Description<br />
Model<br />
noconstant<br />
suppress constant term<br />
pa<br />
use population-averaged estimator<br />
offset(varname) include varname in model with coefficient constrained to 1<br />
asis<br />
retain perfect predictor variables<br />
Correlation<br />
corr(correlation)<br />
force<br />
SE/Robust<br />
vce(vcetype)<br />
nmp<br />
scale(parm)<br />
Reporting<br />
level(#)<br />
or<br />
display options<br />
Optimization<br />
optimize options<br />
nodisplay<br />
coeflegend<br />
within-panel correlation structure<br />
estimate even if observations unequally spaced in time<br />
vcetype may be conventional, robust, bootstrap, or<br />
jackknife<br />
use divisor N − P instead of the default N<br />
overrides the default scale parameter;<br />
parm may be x2, dev, phi, or #<br />
set confidence level; default is level(95)<br />
report odds ratios<br />
control column formats, row spacing, line width, display of omitted<br />
variables and base and empty cells, and factor-variable labeling<br />
control the optimization process; seldom used<br />
do not display the header and coefficients<br />
display legend instead of statistics<br />
correlation<br />
Description<br />
exchangeable<br />
exchangeable<br />
independent<br />
independent<br />
unstructured<br />
unstructured<br />
fixed matname<br />
user-specified<br />
ar # autoregressive of order #<br />
stationary # stationary of order #<br />
nonstationary # nonstationary of order #