Stata 15 help for etregress

[TE] etregress -- Linear regression with endogenous treatment effects

Syntax

Basic syntax

etregress depvar [indepvars], treat(depvar_t = indepvars_t) [twostep|cfunction]

Full syntax for maximum likelihood estimates only

etregress depvar [indepvars] [if] [in] [weight], treat(depvar_t = indepvars_t [, noconstant]) [etregress_ml_options]

Full syntax for two-step consistent estimates only

etregress depvar [indepvars] [if] [in], treat(depvar_t = indepvars_t [, noconstant]) twostep [etregress_ts_options]

Full syntax for control-function estimates only

etregress depvar [indepvars] [if] [in], treat(depvar_t = indepvars_t [, noconstant]) cfunction [etregress_cf_options]

etregress_ml_options Description ------------------------------------------------------------------------- Model * treat() equation for treatment effects noconstant suppress constant term poutcomes use potential-outcome model with separate treatment and control group variance and correlation parameters constraints(constraints) apply specified linear constraints collinear keep collinear variables

SE/Robust vce(vcetype) vcetype may be oim, robust, cluster clustvar, opg, bootstrap, or jackknife

Reporting level(#) set confidence level; default is level(95) first report first-step probit estimates hazard(newvar) create newvar containing hazard from treatment equation lrmodel perform the likelihood-ratio model test instead of the default Wald test nocnsreport do not display constraints 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 maximization process; seldom used

coeflegend display legend instead of statistics ------------------------------------------------------------------------- * treat(depvar_t = indepvars_t[, noconstant]) is required.

etregress_ts_options Description ------------------------------------------------------------------------- Model * treat() equation for treatment effects * twostep produce two-step consistent estimate noconstant suppress constant term

SE vce(vcetype) vcetype may be conventional, bootstrap, or jackknife

Reporting level(#) set confidence level; default is level(95) first report first-step probit estimates hazard(newvar) create newvar containing hazard from treatment equation display_options control columns and column formats, row spacing, line width, display of omitted variables and base and empty cells, and factor-variable labeling

coeflegend display legend instead of statistics ------------------------------------------------------------------------- * treat(depvar_t = indepvars_t[, noconstant]) and twostep are required.

etregress_cf_options Description ------------------------------------------------------------------------- Model * treat() equation for treatment effects * cfunction produce control-function estimate noconstant suppress constant term poutcomes use potential-outcome model with separate treatment and control group variance and correlation parameters

SE vce(vcetype) vcetype may be robust, bootstrap, or jackknife

Reporting level(#) set confidence level; default is level(95) first report first-step probit estimates hazard(newvar) create newvar containing hazard from treatment equation 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 maximization process; seldom used

coeflegend display legend instead of statistics ------------------------------------------------------------------------- * treat(depvar_t = indepvars_t[, noconstant]) and cfunction are required.

indepvars and indepvars_t may contain factor variables; see fvvarlist. depvar, indepvars, depvar_t, and indepvars_t may contain time-series operators; see tsvarlist. bootstrap, by, fp, jackknife, rolling, statsby, and svy are allowed; see prefix. Weights are not allowed with the bootstrap prefix. aweights are not allowed with the jackknife prefix. twostep, cfunction, vce(), first, hazard(), lrmodel, and weights are not allowed with the svy prefix. pweights, aweights, fweights, and iweights are allowed with both maximum likelihood and control-function estimation; see weight. No weights are allowed if twostep is specified. coeflegend does not appear in the dialog box. See [TE] etregress postestimation for features available after estimation.

Menu

Statistics > Treatment effects > Endogenous treatment > Maximum likelihood estimator > Continuous outcomes

Description

etregress estimates an average treatment effect and the other parameters of a linear regression model augmented with an endogenous binary-treatment variable. Estimation is by full maximum likelihood, a two-step consistent estimator, or a control-function estimator.

In addition to the average treatment effect, etregress can be used to estimate the average treatment effect on the treated when the outcome may not be conditionally independent of the treatment.

etreg is a synonym for etregress.

Options for maximum likelihood estimates

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

treat(depvar_t = indepvars_t[, noconstant]) specifies the variables and options for the treatment equation. It is an integral part of specifying a treatment-effects model and is required.

noconstant; see [R] estimation options.

poutcomes specifies that a potential-outcome model with separate variance and correlation parameters for each of the treatment and control groups be used.

constraints(constraints), collinear; see [R] estimation options.

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

vce(vcetype) specifies the type of standard error reported, which includes types that are derived from asymptotic theory (oim, opg), 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.

first specifies that the first-step probit estimates of the treatment equation be displayed before estimation.

hazard(newvar) will create a new variable containing the hazard from the treatment equation. The hazard is computed from the estimated parameters of the treatment equation.

lrmodel, nocnsreport; see [R] estimation options.

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: difficult, technique(algorithm_spec), iterate(#), [no]log, trace, gradient, showstep, hessian, showtolerance, tolerance(#), ltolerance(#), nrtolerance(#), nonrtolerance(#), and from(init_specs); see [R] maximize. These options are seldom used.

Setting the optimization type to technique(bhhh) resets the default vcetype to vce(opg).

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

coeflegend; see [R] estimation options.

Options for two-step consistent estimates

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

treat(depvar_t = indepvars_t[, noconstant]) specifies the variables and options for the treatment equation. It is an integral part of specifying a treatment-effects model and is required.

twostep specifies that two-step consistent estimates of the parameters, standard errors, and covariance matrix be produced, instead of the default maximum likelihood estimates.

noconstant; see [R] estimation options.

+----+ ----+ SE +---------------------------------------------------------------

vce(vcetype) specifies the type of standard error reported, which includes types that are derived from asymptotic theory (conventional) and that use bootstrap or jackknife methods (bootstrap, jackknife); see [R] vce_option.

vce(conventional), the default, uses the conventionally derived variance estimator for the two-step estimator of the treatment-effects model.

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

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

first specifies that the first-step probit estimates of the treatment equation be displayed before estimation.

hazard(newvar) will create a new variable containing the hazard from the treatment equation. The hazard is computed from the estimated parameters of the treatment equation.

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.

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

coeflegend; see [R] estimation options.

Options for control-function estimates

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

treat(depvar_t = indepvars_t[, noconstant]) specifies the variables and options for the treatment equation. It is an integral part of specifying a treatment-effects model and is required.

cfunction specifies that control-function estimates of the parameters, standard errors, and covariance matrix be produced instead of the default maximum likelihood estimates. cfunction is required.

noconstant; see [R] estimation options.

poutcomes specifies that a potential-outcome model with separate variance and correlation parameters for each of the treatment and control groups be used.

+----+ ----+ SE +---------------------------------------------------------------

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

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

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

first specifies that the first-step probit estimates of the treatment equation be displayed before estimation.

hazard(newvar) will create a new variable containing the hazard from the treatment equation. The hazard is computed from the estimated parameters of the treatment equation.

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

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

coeflegend; see [R] estimation options.

Examples

--------------------------------------------------------------------------- Setup . webuse union3

Obtain full ML estimates . etregress wage age grade smsa black tenure, treat(union = south black tenure)

Obtain two-step consistent estimates . etregress wage age grade smsa black tenure, treat(union = south black tenure) twostep

--------------------------------------------------------------------------- Setup . webuse drugexp

Obtain control-function estimates for potential-outcome model . etregress lndrug chron age lninc, treat(ins=age married lninc work) poutcomes cfunction

---------------------------------------------------------------------------

Stored results

etregress (maximum likelihood) stores the following in e():

Scalars e(N) number of observations e(k) number of parameters e(k_eq) number of equations in e(b) e(k_eq_model) number of equations in overall model test e(k_aux) number of auxiliary parameters e(k_dv) number of dependent variables e(df_m) model degrees of freedom e(ll) log likelihood e(ll_0) log likelihood, constant-only model (lrmodel only) e(N_clust) number of clusters e(lambda) estimate of lambda in constrained model e(selambda) standard error of lambda in constrained model e(sigma) estimate of sigma in constrained model e(lambda0) estimate of lambda0 in potential-outcome model e(selambda0) standard error of lambda0 in potential-outcome model e(sigma0) estimate of sigma0 in potential-outcome model e(lambda1) estimate of lambda1 in potential-outcome model e(selambda1) standard error of lambda1 in potential-outcome model e(sigma1) estimate of sigma1 in potential-outcome model e(chi2) chi-squared e(chi2_c) chi-squared for comparison test e(p) p-value for model test e(p_c) p-value for comparison test e(rho) estimate of rho in constrained model e(rho0) estimate of rho0 in potential-outcome model e(rho1) estimate of rho1 in potential-outcome model e(rank) rank of e(V) e(rank0) rank of e(V) for constant-only model e(ic) number of iterations e(rc) return code e(converged) 1 if converged, 0 otherwise

Macros e(cmd) etregress e(cmdline) command as typed e(depvar) name of dependent variable e(hazard) variable containing hazard e(wtype) weight type e(wexp) weight expression e(title) title in estimation output e(title2) secondary title in estimation output e(clustvar) name of cluster variable e(chi2type) Wald or LR; type of model chi-squared test e(chi2_ct) Wald or LR; type of model chi-squared test corresponding to e(chi2_c) e(vce) vcetype specified in vce() e(vcetype) title used to label Std. Err. e(opt) type of optimization e(which) max or min; whether optimizer is to perform maximization or minimization e(method) ml e(ml_method) type of ml method e(user) name of likelihood-evaluator program e(technique) maximization technique e(properties) b V e(predict) program used to implement predict e(footnote) program used to implement the footnote display e(marginsok) predictions allowed by margins e(asbalanced) factor variables fvset as asbalanced e(asobserved) factor variables fvset as asobserved

Matrices e(b) coefficient vector e(Cns) constraints matrix e(ilog) iteration log (up to 20 iterations) e(gradient) gradient vector e(V) variance-covariance matrix of the estimators e(V_modelbased) model-based variance

Functions e(sample) marks estimation sample

etregress (two-step) stores the following in e():

Scalars e(N) number of observations e(df_m) model degrees of freedom e(lambda) lambda e(selambda) standard error of lambda e(sigma) estimate of sigma e(chi2) chi-squared e(p) p-value for model test e(rho) rho e(rank) rank of e(V)

Macros e(cmd) etregress e(cmdline) command as typed e(depvar) name of dependent variable e(hazard) variable containing hazard e(title) title in estimation output e(title2) secondary title in estimation output e(chi2type) Wald or LR; type of model chi-squared test e(vce) vcetype specified in vce() e(method) twostep e(properties) b V e(predict) program used to implement predict e(footnote) program used to implement the footnote display e(marginsok) predictions allowed by margins 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

etregress (control-function) stores the following in e():

Scalars e(N) number of observations e(k) number of parameters e(k_eq) number of equations in e(b) e(k_aux) number of auxiliary parameters e(k_dv) number of dependent variables e(lambda) estimate of lambda in constrained model e(selambda) standard error of lambda in constrained model e(sigma) estimate of sigma in constrained model e(lambda0) estimate of lambda0 in potential-outcome model e(selambda0) standard error of lambda0 in potential-outcome model e(sigma0) estimate of sigma0 in potential-outcome model e(lambda1) estimate of lambda1 in potential-outcome model e(selambda1) standard error of lambda1 in potential-outcome model e(sigma1) estimate of sigma1 in potential-outcome model e(chi2_c) chi-squared for comparison test e(p_c) p-value for comparison test e(rho) estimate of rho in constrained model e(rho0) estimate of rho0 in potential-outcome model e(rho1) estimate of rho1 in potential-outcome model e(rank) rank of e(V) e(converged) 1 if converged, 0 otherwise

Macros e(cmd) etregress e(cmdline) command as typed e(depvar) name of dependent variable e(hazard) variable containing hazard e(wtype) weight type e(wexp) weight expression e(title) title in estimation output e(title2) secondary title in estimation output e(chi2_ct) Wald; type of model chi-squared test corresponding to e(chi2_c) e(vce) vcetype specified in vce() e(vcetype) title used to label Std. Err. e(method) cfunction e(properties) b V e(predict) program used to implement predict e(footnote) program used to implement the footnote display e(marginsok) predictions allowed 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