[R] bootstrap postestimation -- Postestimation tools for bootstrap
Postestimation commands
The following postestimation command is of special interest after
bootstrap:
Command Description
-------------------------------------------------------------------------
estat bootstrap percentile-based and bias-corrected CI tables
-------------------------------------------------------------------------
The following standard postestimation commands are also available:
Command Description
-------------------------------------------------------------------------
contrast contrasts and ANOVA-style joint tests of estimates
estat ic Akaike's and Schwarz's Bayesian information
criteria (AIC and BIC)
estat summarize summary statistics for the estimation sample
estat vce variance-covariance matrix of the estimators (VCE)
estimates cataloging estimation results
hausman Hausman's specification test
lincom point estimates, standard errors, testing, and
inference for linear combinations of coefficients
margins marginal means, predictive margins, marginal
effects, and average marginal effects
marginsplot graph the results from margins (profile plots,
interaction plots, etc.)
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
pwcompare pairwise comparisons of estimates
test Wald tests of simple and composite linear
hypotheses
testnl Wald tests of nonlinear hypotheses
-------------------------------------------------------------------------
The postestimation command is allowed if it may be used after command.
predict
The syntax of predict (and even if predict is allowed) following
bootstrap depends upon the command used with bootstrap. If predict is
not allowed, neither is predictnl.
margins
The syntax of margins (and even if margins is allowed) following
bootstrap depends upon the command used with bootstrap.
Syntax for estat
estat bootstrap [, options]
options Description
-------------------------------------------------------------------------
bc bias-corrected CIs; the default
bca bias-corrected and accelerated (BC_a) CIs
normal normal-based CIs
percentile percentile CIs
all all available CIs
noheader suppress table header
nolegend suppress table legend
verbose display the full table legend
-------------------------------------------------------------------------
bc, bca, normal, and percentile may be used together.
Menu for estat
Statistics > Postestimation
Description for estat
estat bootstrap displays a table of confidence intervals for each
statistic from a bootstrap analysis.
Options for estat bootstrap
bc is the default and displays bias-corrected confidence intervals.
bca displays bias-corrected and accelerated confidence intervals. This
option assumes that you also specified the bca option on the
bootstrap prefix command.
normal displays normal approximation confidence intervals.
percentile displays percentile confidence intervals.
all displays all available confidence intervals.
noheader suppresses display of the table header. This option implies
nolegend.
nolegend suppresses display of the table legend, which identifies the
rows of the table with the expressions they represent.
verbose requests that the full table legend be displayed.
Examples
Setup
. sysuse auto
. bootstrap, reps(100) bca: regress mpg weight gear foreign
Obtain bias-corrected CIs
. estat bootstrap
Obtain bias-corrected and accelerated CIs
. estat bootstrap, bca
Obtain all available CIs
. estat bootstrap, all
Test that coefficients on gear and foreign sum to 0
. test gear + foreign = 0
Compute estimate, SE, test statistic, significance level, and CI for the
ratio of coefficient of gear_ratio to the coefficient of foreign
. nlcom _b[gear_ratio] / _b[foreign]