help xtabond postestimation dialogs: predict estat
also see: xtabond
-------------------------------------------------------------------------------
Title
[XT] xtabond postestimation -- Postestimation tools for xtabond
Description
The following postestimation commands are of special interest after
xtabond:
command description
-------------------------------------------------------------------------
estat abond test for autocorrelation
estat sargan Sargan test of overidentifying restrictions
-------------------------------------------------------------------------
The following standard postestimation commands are also available:
command description
-------------------------------------------------------------------------
estat VCE and estimation sample summary
estimates cataloging estimation results
lincom point estimates, standard errors, testing, and inference for
linear combinations of coefficients
margins marginal means, predictive margins, marginal effects, and
average marginal effects
nlcom point estimates, standard errors, testing, and inference for
nonlinear combinations of coefficients
predict predictions, residuals, influence statistics, and other
diagnostic measures
predictnl point estimates, standard errors, testing, and inference for
generalized predictions
test Wald tests of simple and composite linear hypotheses
testnl Wald tests of nonlinear hypotheses
-------------------------------------------------------------------------
Special-interest postestimation commands
estat abond reports the Arellano-Bond test for serial correlation in the
first-differenced residuals.
estat sargan reports the Sargan test of the overidentifying restrictions.
Syntax for predict
predict [type] newvar [if] [in] [, xb e stdp difference]
Menu
Statistics > Postestimation > Predictions, residuals, etc.
Options for predict
+------+
----+ Main +-------------------------------------------------------------
xb, the default, calculates the linear prediction.
e calculates the residual error.
stdp calculates the standard error of the prediction, which can be
thought of as the standard error of the predicted expected value or
mean for the observation's covariate pattern. The standard error of
the prediction is also referred to as the standard error of the
fitted value. stdp may not be combined with difference.
difference specifies that the statistic be calculated for the first
differences instead of the levels, the default.
Syntax for estat abond
estat abond [, artests(#)]
Menu
Statistics > Postestimation > Reports and statistics
Option for estat abond
artests(#) specifies the highest order of serial correlation to be
tested. By default, the tests computed during estimation are
reported. The model will be refit when artests(#) specifies a higher
order than that computed during the original estimation. The model
can be refit only if the data have not changed.
Remarks for estat abond
After the one-step system estimator, the test can be computed only when
vce(robust) has been specified. (The system estimator is used to
estimate the constant in xtabond.)
Syntax for estat sargan
estat sargan
Menu
Statistics > Postestimation > Reports and statistics
Examples
Setup
. webuse abdata, clear
Fit a model and obtain default AR tests
. xtabond n w k, twostep
. estat abond
Request a higher order than originally computed
. estat abond, artests(3)
Obtain the Sargan test
. estat sargan
Compute the linear prediction
. predict nhat, xb
Fit a model including both w and the first lag of w as regressors,
obtaining a Windmeijer-corrected robust VCE, and then test the joint
significance of w and L.w
. xtabond n L(0/1).w k, twostep vce(robust)
. test D1.w = 0, notest
. test LD.w = 0, accumulate
Also see
Manual: [XT] xtabond postestimation
Help: [XT] xtabond
