[ERM] estat teffects -- Average treatment effects for extended regression
estat teffects [, options]
ate estimate average treatment effect; the default
atet estimate average treatment effect on the treated
pomean estimate potential-outcome mean
tlevel(numlist) calculate treatment effects or potential-outcome
means for specified treatment levels
outlevel(numlist) calculate treatment effects or potential-outcome
means for specified levels of ordinal dependent
subpop(subspec) estimate for subpopulation
level(#) set confidence level; default is level(95)
display_options control columns and column formats, row spacing,
line width and factor-variable labeling
Statistics > Postestimation
estat teffects estimates the average treatment effect, average treatment
effect on the treated, and potential-outcome mean for ERMs.
ate estimates the average treatment effect (ATE). This is the default.
atet estimates the average treatment effect on the treated (ATET). For
binary treatments, the ATET is reported for the treated group
subpopulation. For ordinal treatments, by default, the ATET is
reported for the first noncontrol treatment group subpopulation. You
can use the subpop() option to calculate the ATET for a different
pomean estimates the potential-outcome mean (POM).
tlevel(numlist) specifies the treatment levels for which treatment
effects or POMs are calculated. By default, the treatment effects
are computed for all noncontrol treatment levels, and the POMs are
computed for all treatment levels.
outlevel(numlist) specifies the levels of the ordinal dependent variable
for which treatment effects or POMs are to be calculated. By
default, treatment effects or POMs are computed for all levels of the
ordinal dependent variable. This option is only available after
subpop([varname] [if]) specifies the subpopulation for which the ATE,
ATET, and POM are calculated. The subpopulation is identified by the
indicator variable, by the if expression, or by both. A 0 indicates
that the observation be excluded, a nonzero indicates that it be
included, and a missing value indicates that it be treated as outside
of the population (and thus ignored). For instance, for an ordinal
treatment trtvar with levels 1, 2, and 3, you can specify subpop(if
trtvar==3) to obtain the ATETs for trtvar = 3.
level(#) specifies the confidence level, as a percentage, for confidence
intervals. The default is level(95) or as set by set level.
display_options: noci, nopvalues, vsquish, nofvlabel, fvwrap(#),
fvwrapon(style), cformat(fmt), pformat(%fmt), sformat(%fmt), and
noci suppresses confidence intervals from being reported in the
nopvalues suppresses p-values and their test statistics from being
reported in the coefficient table.
vsquish specifies that the blank space separating factor-variable
terms or time-series-operated variables from other variables in
the model be suppressed.
nofvlabel displays factor-variable level values rather than attached
value labels. This option overrides the fvlabel setting; see [R]
fvwrap(#) allows long value labels to wrap the first # lines in the
coefficient table. This option overrides the fvwrap setting; see
[R] set showbaselevels.
fvwrapon(style) specifies whether value labels that wrap will break
at word boundaries or break based on available space.
fvwrapon(word), the default, specifies that value labels break at
fvwrapon(width) specifies that value labels break based on
This option overrides the fvwrapon setting; see [R] set
cformat(%fmt) specifies how to format estimates, standard errors, and
confidence limits in the estimates table. The maximum format
width is 9.
pformat(%fmt) specifies how to format p-values in the estimates
table. The maximum format width is 5.
sformat(%fmt) specifies how to format test statistics in the
estimates table. The maximum format width is 8.
nolstretch specifies that the width of the estimates table not be
automatically widened to accommodate longer variable names. The
default, lstretch, is to automatically widen the estimates table
up to the width of the Results window. To change the default,
use set lstretch off. nolstretch is not shown in the dialog box.
. webuse wageed
. eregress wage c.age##c.age tenure, extreat(college) vce(robust)
Average treatment effect on the treated
. estat teffects, atet
Average treatment effect
. estat teffects
estat teffects stores the following in r():
r(vce) vcetype specified in vce()
r(vcetype) title used to label Std. Err.
r(clustvar) name of cluster variable
r(V) variance-covariance matrix of the estimates
r(table) matrix containing the estimates with their standard
errors, test statistics, p-values, and confidence