{smcl}
{* 1Feb2010}{...}
{hline}
help for {hi:xtoverid}
{hline}
{title:Tests of overidentifying restrictions after {cmd:xtreg}, {cmd:xtivreg}, {cmd:xtivreg2} and {cmd:xthtaylor}}
{p 8 14}{cmd:xtoverid}{bind: [, {cmdab:r:obust}} {cmdab:cl:uster}{bind:{cmd:(}{it:varlist}{cmd:)} ]}
{p}{cmd:xtoverid} does not support IV estimation with weights.
{title:Description}
{p}{cmd:xtoverid} computes versions of
a test of overidentifying restrictions (orthogonality conditions)
for a panel data estimation.
For an instrumental variables estimation,
this is a test of the null hypothesis that
the excluded instruments are valid instruments,
i.e., uncorrelated with the error term and correctly excluded
from the estimated equation.
The test statistic is distributed as chi-squared
with degrees of freedom = L-K,
where L is the number of excluded instruments
and K is the number of regressors,
and a rejection casts doubt on the validity of the instruments.
A test of fixed vs. random effects
is also a test of overidentifying restrictions,
and {cmd:xtoverid} will report this test
after a standard panel data estimation with {cmd:xtreg,re}.
{p}If the original estimation reported classical (non-robust) standard errors,
{cmd:xtoverid} will report Sargan's statistic.
The version of this test that is robust to heteroskedasticity
in the errors is Hansen's J statistic,
which is what {cmd:xtoverid} reports if the original estimation
was {cmd:robust} or if {cmd:xtoverid} is called with the {cmd:robust} option.
Similarly, {cmd:xtoverid} will report an overidentification statistic
that is robust to arbitrary heteroskedasticity and within-group correlation
if the {cmd:cluster} option was used by the original estimation or
by the call to {cmd:xtoverid}.
Under the assumption of conditional homoskedasticity,
Sargan's statistic becomes Hansen's J (see Hayashi (2000), p. 227-28),
and hence the two statistics are sometimes referred to
as the Sargan-Hansen or Hansen-Sargan statistic.
The tests are implemented in {cmd:xtoverid}
by calls to the {cmd:ivreg2} of Baum-Schaffer-Stillman.
For further discussion and details of how the test is implemented,
see help {help ivreg2} and Baum et al. (2003, 2006).
{p}A test of fixed vs. random effects
can also be seen as a test of overidentifying restrictions.
The fixed effects estimator uses the orthogonality conditions
that the regressors are uncorrelated with the idiosyncratic error e_it,
i.e., E(X_it*e_it)=0.
The random effects estimator uses the additional orthogonality conditions
that the regressors are uncorrelated with the group-specific error u_i (the "random effect"),
i.e., E(X_it*u_i)=0.
These additional orthogonality conditions are overidentifying restrictions.
The test is implemented by {cmd:xtoverid}
using the artificial regression approach described by
Arellano (1993) and Wooldridge (2002, pp. 290-91),
in which a random effects equation is reestimated
augmented with additional variables consisting of
the original regressors transformed into deviations-from-mean form.
The test statistic is a Wald test
of the significance of these additional regressors.
A large-sample chi-squared test statistic is reported
with no degrees-of-freedom corrections.
Under conditional homoskedasticity,
this test statistic is asymptotically equivalent to
the usual Hausman fixed-vs-random effects test;
with a balanced panel,
the artificial regression and Hausman test statistics are numerically equal.
See Arellano (1993) for an exact statement
and the example below for a demonstration.
Unlike the Hausman version,
the test reported by {cmd:xtoverid}
extends straightforwardly to heteroskedastic- and cluster-robust versions,
and is guaranteed always to generate a nonnegative test statistic.
The remainder of this help file discusses how the variables are transformed
prior to IV estimation and special issues that arise.
{p}The official Stata routines {cmd:xtivreg} and {cmd:xthtaylor}
work by transforming the variables in the regression,
constructing the instruments,
and then estimating a standard single equation IV estimation
on the transformed variables;
{cmd:xtoverid} works the same way,
and includes an internal check that the IV estimation
matches the original estimation
for which the overidentification statistic is being requested.
{p}For fixed-effects IV estimation ({cmd:xtivreg,fe} or {cmd:xtivreg2,fe}),
the "within transformation" is first applied to the data,
i.e., all variables have group means subtracted,
and then an IV estimation is performed on the demeaned data.
The between IV estimator ({cmd:xtivreg,be}) is an IV estimation on group means,
the first differences IV estimator ({cmd:xtivreg,fd} or {cmd:xtivreg2,fd})
is an IV estimation on first differences
and the default G2SLS random-effects estimator ({cmd:xtivreg,re})
is an IV estimation on variables subjected to the GLS transform.
In all these estimators,
the excluded instruments are subject to the same transformations
as the regressors and dependent variable.
Note that the overidentification statistic
reported after a fixed effects estimation
with either classical or {cmd:robust} standard errors
will incorporate a degrees-of-freedom adjustment
deriving from the degrees of freedom lost to the number of fixed effects.
No adjustment is made (or is required) for a {cmd:cluster}-robust
overidentification statistic.
See {help xtivreg2} for further discussion and details.
{p}The GLS IV estimators {cmd:xtivreg,ec2sls} and {cmd:xthtaylor}
are slightly different:
the dependent variables and regressors are subjected to the GLS transform,
but the instrument sets are combinations of
demeaned and group mean (or time-invariant) variables.
The degrees of freedom of the overidentification statistic
for the standard Hausman-Taylor estimator
is K1-G2, where K1 is the number of exogenous time-varying variables
and G2 is the number of endogenous time-invariant variables.
In the Amemiya-MaCurdy version of the estimator
(available via {cmd:xthtaylor,amacurdy}),
the degrees of freedom will be T*K1-G2,
where T is the length of the panel in the time dimension.
For further discussion,
see the Stata manual entries for these estimators
or Baltagi (2005).
{p}Note that following estimation by {cmd:xtivreg,ec2sls},
the number of degrees of freedom of the overidentification statistic
is not what is expected based on a simple count of instruments and endogenous variables
when the equation includes an exogenous regressor.
The reason is that in EC2SLS estimation as implemented in {cmd:xtivreg,ec2sls},
the regressor is subject to the GLS transform
and then, in the IV estimation on the transformed data,
is treated as an {it:endogenous} regressor with
both its demeaned and recentered transformation
and its group mean transformation
as {it:two} excluded instruments.
When estimating using {cmd:xtivreg,ec2sls}
on an unbalanced panel, therefore,
including exogenous regressors increases the number
of degrees of freedom of the overidentification statistic.
The intuition is that exogenous regressors in EC2SLS estimation
are overidentified for the same reason that exogenous regressors
in a standard random effects estimation are overidentified (see above).
See the examples below.
{title:Options}
{p 0 4}{cmd:robust} requests a heteroskedastic-robust overidentification statistic.
{p 0 4}{cmd:cluster(}{it:varlist}{cmd:)} requests an overidentification statistic
that is robust to arbitrary heteroskedasticity and within-group correlation,
where the group is defined by {it:varlist}.
If {cmd:ivreg2} version 3.0 or later is installed, 2-way clustering is supported;
see help {help ivreg2} for details.
{title:Examples}
{phang}{stata webuse nlswork : . webuse nlswork}
{phang}{stata tsset idcode year : . tsset idcode year}
{phang}{stata gen age2=age^2 : . gen age2=age^2}
{phang}{stata gen black=(race==2) : . gen black=(race==2)}
{phang}{stata xtivreg ln_wage age (tenure = union south), fe i(idcode): . xtivreg ln_wage age (tenure = union south), fe i(idcode)}
{phang}{stata xtoverid : . xtoverid}
{phang}{stata xtoverid, robust : . xtoverid, robust}
{phang}{stata xtoverid, cluster(idcode) : . xtoverid, cluster(idcode)}
(Identical to overid stat from xtivreg2 with same options)
{phang}{stata xtivreg2 ln_wage age (tenure = union south), fe cluster(idcode) : . xtivreg2 ln_wage age (tenure = union south), fe cluster(idcode)}
(Compare overid stat degrees of freedom for G2SLS:)
(2 (union, south) - 1 (tenure) = 1)
{phang}{stata xtivreg ln_wage age (tenure = union south), re : . xtivreg ln_wage age (tenure = union south), re}
{phang}{stata xtoverid : . xtoverid}
(...with degrees of freedom for EC2SLS:)
(6 (mean and mean-deviation of union, south, age) - 2 (GLS transform of tenure, age) = 4)
{phang}{stata xtivreg ln_wage age (tenure = union south), ec2sls : . xtivreg ln_wage age (tenure = union south), ec2sls}
{phang}{stata xtoverid : . xtoverid}
(Changing the number of included exogenous variables changes the dof of the overid stat)
(4 (mean and mean-deviation of union, south) - 1 (GLS transform of tenure) = 3)
{phang}{stata xtivreg ln_wage (tenure = union south), ec2sls : . xtivreg ln_wage (tenure = union south), ec2sls}
{phang}{stata xtoverid : . xtoverid}
(Hausman-Taylor estimation)
(dof = 2 (exogenous time-varying age, age2) - 1 (endogenous time-invariant grade) = 1)
{phang}{stata xthtaylor ln_wage age age2 tenure hours black birth_yr grade, endog(tenure hours grade) i(idcode) : . xthtaylor ln_wage age age2 tenure hours black birth_yr grade, endog(tenure hours grade) i(idcode) }
{phang}{stata xtoverid : . xtoverid}
(Equivalence of xtoverid statistic and standard Hausman fixed-vs-random effects test)
{phang}{stata webuse abdata : . webuse abdata}
(Balanced panel)
{phang}{stata xtreg n w k if year>=1978 & year<=1982, re : . xtreg n w k if year>=1978 & year<=1982, re}
(Artificial regression overid test of fixed-vs-random effects)
{phang}{stata xtoverid : . xtoverid}
{phang}{stata di r(j) : . di r(j)}
{phang}{stata est store re : . est store re}
{phang}{stata xtreg n w k if year>=1978 & year<=1982, fe : . xtreg n w k if year>=1978 & year<=1982, fe}
{phang}{stata est store fe : . est store fe}
(In homoskedastic balanced panel case, Hausman test using sigma from FE estimation...)
{phang}{stata hausman fe re, sigmaless : . hausman fe re, sigmaless}
(... is numerically equal to the artificial regression overid statistic)
{phang}{stata di r(chi2) : . di r(chi2)}
(Artificial regression overid statistic readily extends to non-homoskedastic case)
{phang}{stata xtreg n w k, re cluster(id) : . xtreg n w k, re cluster(id) }
{phang}{stata xtoverid : . xtoverid}
{title:Citation}
{p}{cmd:xtoverid} is not an official Stata command.
It is a free contribution to the research community, like a paper.
Please cite it as such:{p_end}
{phang}Schaffer, M.E., Stillman, S. 2010. xtoverid:
Stata module to calculate tests of overidentifying restrictions
after xtreg, xtivreg, xtivreg2 and xthtaylor
{browse "http://ideas.repec.org/c/boc/bocode/s456779.html":http://ideas.repec.org/c/boc/bocode/s456779.html}{p_end}
{title:References}
{p 0 4}Arellano, M. 1993. On the testing of correlated effects with panel data.
Journal of Econometrics, Vol. 59, Nos. 1-2, pp. 87-97.
{p 0 4}Baltagi, B. 2005. Econometric analysis of danel data.
New York: Wiley.
{p 0 4}Baum, C. F., Schaffer, M. E., Stillman, S. 2003. Instrumental variables and GMM:
Estimation and testing.
{browse "http://ideas.repec.org/a/tsj/stataj/v3y2003i1p1-31.html":The Stata Journal, Vol. 3, No. 1, pp. 1-31}.
Unpublished working paper version:
{browse "http://ideas.repec.org/p/boc/bocoec/545.html":Boston College Department of Economics Working Paper No 545}.
{p 0 4}Baum, C. F., Schaffer, M. E., Stillman, S., 2006. Enhanced routines for
instrumental variables/GMM estimation and testing. Unpublished working paper,
forthcoming.
{p 0 4}Hayashi, F. 2000. Econometrics. Princeton: Princeton University Press.
{p 0 4}Wooldridge, J.M. 2002. Econometric Analysis of Cross Section and Panel Data.
Cambridge, MA: MIT Press.
{title:Authors}
Mark E Schaffer, Heriot-Watt University, UK
m.e.schaffer@hw.ac.uk
Steven Stillman, Motu Economic and Public Policy Research, NZ
stillman@motu.org.nz
{title:Also see}
{p 1 14}Manual: {hi:[R] ivreg}{p_end}
{p 0 19}On-line: help for {help xtivreg}; {help xtivreg2} (if installed);
{help xthtaylor}; {help ivreg2} (if installed);{p_end}