Stata 15 help for stteffects ipw

[TE] stteffects ipw -- Survival-time inverse-probability weighting


stteffects ipw (tvar tmvarlist [, tmoptions]) (cmvarlist [, cmoptions]) [if] [in] [, stat options]

tvar must contain integer values representing the treatment levels.

tmvarlist specifies the variables that predict treatment assignment in the treatment model.

cmvarlist specifies the variables that predict censoring in the censoring model.

tmoptions Description ------------------------------------------------------------------------- Model logit logistic treatment model; the default probit probit treatment model hetprobit(varlist) heteroskedastic probit treatment model noconstant suppress constant from treatment model -------------------------------------------------------------------------

cmoptions Description ------------------------------------------------------------------------- Model weibull Weibull; the default exponential exponential gamma two-parameter gamma lnormal lognormal ancillary(avarlist[, noconstant]) specify variables used to model ancillary parameter noconstant suppress constant from censoring model -------------------------------------------------------------------------

stat Description ------------------------------------------------------------------------- Stat ate estimate average treatment effect in population; the default atet estimate average treatment effect on the treated pomeans estimate potential-outcome means -------------------------------------------------------------------------

options Description ------------------------------------------------------------------------- SE/Robust vce(vcetype) vcetype may be robust, cluster clustvar, bootstrap, or jackknife

Reporting level(#) set confidence level; default is level(95) aequations display auxiliary-equation results noshow do not show st setting information display_options control columns and column formats, row spacing, line width, display of omitted variables and base and empty cells, and factor-variable labeling

Maximization maximize_options control the maximization process; seldom used iterinit(#) specify starting-value iterations; seldom used

Advanced pstolerance(#) set tolerance for overlap assumption osample(newvar) identify observations that violate the overlap assumption control(#|label) specify the level of tvar that is the control tlevel(#|label) specify the level of tvar that is the treatment

coeflegend display legend instead of statistics -------------------------------------------------------------------------

You must stset your data before using stteffects; see [ST] stset. tmvarlist, cmvarlist, and avarlist may contain factor variables; see fvvarlists. bootstrap, by, jackknife, and statsby are allowed; see prefix. Weights are not allowed with the bootstrap prefix. fweights, iweights, and pweights may be specified using stset; see Weights under Remarks and examples in [ST] stset. However, weights may not be specified if you are using the bootstrap prefix. coeflegend does not appear in the dialog box. See [TE] stteffects postestimation for features available after estimation.


Statistics > Treatment effects > Survival outcomes > Inverse-probability weighting (IPW)


stteffects ipw estimates the average treatment effect, the average treatment effect on the treated, and the potential-outcome means from observational survival-time data with random time to censoring. Estimation is by inverse-probability weighting. Inverse-probability weighting estimators use weighted averages of the observed outcome. The estimated weights correct for missing data on the potential outcomes and for censored survival times. stteffects ipw offers several choices for the functional forms of the treatment model and the time-to-censoring model. Binary and multivalued treatments are accommodated.

See [TE] stteffects intro for an overview of estimating treatment effects from observational survival-time data.


+-------+ ----+ Model +------------------------------------------------------------

ancillary(avarlist[, noconstant]) specifies the variables used to model the ancillary parameter. By default, the ancillary parameter does not depend on covariates. Specifying ancillary(avarlist, noconstant) causes the constant to be suppressed in the model for the ancillary parameter.

noconstant; see [R] estimation options.

+------+ ----+ Stat +-------------------------------------------------------------

stat is one of three statistics: ate, atet, or pomeans. ate is the default.

ate specifies that the average treatment effect be estimated.

atet specifies that the average treatment effect on the treated be estimated.

pomeans specifies that the potential-outcome means for each treatment level be estimated.

+-----------+ ----+ SE/Robust +--------------------------------------------------------

vce(vcetype) specifies the type of standard error reported, which includes types that are robust to some kinds of misspecification (robust), that allow for intragroup correlation (cluster clustvar), and that use bootstrap or jackknife methods (bootstrap, jackknife); see [R] vce_option.

+-----------+ ----+ Reporting +--------------------------------------------------------

level(#); see [R] estimation options.

aequations specifies that the results for the outcome-model or the treatment-model parameters be displayed. By default, the results for these auxiliary parameters are not displayed.

noshow prevents stteffects ipw from showing the key st variables. This option is rarely used because most people type stset, show or stset, noshow to permanently set whether they want to see these variables mentioned at the top of the output of every st command; see [ST] stset.

display_options: noci, nopvalues, noomitted, vsquish, noemptycells, baselevels, allbaselevels, nofvlabel, fvwrap(#), fvwrapon(style), cformat(%fmt), pformat(%fmt), sformat(%fmt), and nolstretch; see [R] estimation options.

+--------------+ ----+ Maximization +-----------------------------------------------------

maximize_options: iterate(#), [no]log, and from(init_specs); see [R] maximize. These options are seldom used.

init_specs is one of

matname [, skip copy]

# [, # ...], copy

iterinit(#) specifies the maximum number of iterations used to calculate the starting values. This option is seldom used.

+----------+ ----+ Advanced +---------------------------------------------------------

pstolerance(#) specifies the tolerance used to check the overlap assumption. The default value is pstolerance(1e-5). stteffects will exit with an error if an observation has an estimated propensity score smaller than that specified by pstolerance().

osample(newvar) specifies that indicator variable newvar be created to identify observations that violate the overlap assumption.

control(#|label) specifies the level of tvar that is the control. The default is the first treatment level. You may specify the numeric level # (a nonnegative integer) or the label associated with the numeric level. control() may not be specified with statistic pomeans. control() and tlevel() may not specify the same treatment level.

tlevel(#|label) specifies the level of tvar that is the treatment for the statistic atet. The default is the second treatment level. You may specify the numeric level # (a nonnegative integer) or the label associated with the numeric level. tlevel() may only be specified with statistic atet. tlevel() and control() may not specify the same treatment level.

The following option is available with stteffects but is not shown in the dialog box:

coeflegend; [R] estimation options.


Setup . webuse sheart

Estimate the ATE, modeling the treatment assignment using the default logit model . stteffects ipw (smoke age exercise education) (age exercise diet education)

Estimate the ATE, using the probit model for the treatment assignment and using a gamma model for the censoring time . stteffects ipw (smoke age exercise education, probit) (age exercise diet education, gamma)

Estimate the ATET, modeling the treatment assignment using the default logit model . stteffects ipw (smoke age exercise education) (age exercise diet education), atet

Stored results

stteffects ipw stores the following in e():

Scalars e(N) number of observations e(nj) number of observations for treatment level j e(N_clust) number of clusters e(k_eq) number of equations in e(b) e(k_levels) number of levels in treatment variable e(treated) level of treatment variable defined as treated e(control) level of treatment variable defined as control e(converged) 1 if converged, 0 otherwise

Macros e(cmd) stteffects e(cmdline) command as typed e(dead) _d e(depvar) _t e(tvar) name of treatment variable e(subcmd) ipw e(tmodel) treatment model: logit, probit, or hetprobit e(cmodel) censoring model: weibull, exponential, gamma, or lognormal e(stat) statistic estimated: ate, atet, or pomeans e(wtype) weight type e(wexp) weight expression e(title) title in estimation output e(clustvar) name of cluster variable e(tlevels) levels of treatment variable e(vce) vcetype specified in vce() e(vcetype) title used to label Std. Err. e(properties) b V e(estat_cmd) program used to implement estat e(predict) program used to implement predict e(marginsnotok) predictions disallowed by margins e(asbalanced) factor variables fvset as asbalanced e(asobserved) factor variables fvset as asobserved

Matrices e(b) coefficient vector e(V) variance-covariance matrix of the estimators

Functions e(sample) marks estimation sample

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index