help anova postestimation dialogs: predict test dfbeta estat
plot dialogs: acprplot avplots cprplot
lvr2plot rvfplot rvpplot
also see: anova
-------------------------------------------------------------------------------
Title
[R] anova postestimation -- Postestimation tools for anova
Description
The following postestimation commands are of special interest after
anova:
command options
-------------------------------------------------------------------------
dfbeta DFBETA influence statistics
estat hettest tests for heteroskedasticity
estat imtest information matrix test
estat ovtest Ramsey regression specification-error test for omitted
variables
estat szroeter Szroeter's rank test for heteroskedasticity
estat vif variance inflation factors for the independent
variables
acprplot augmented component-plus-residual plot
avplot added-variable plot
avplots all added-variable plots in one image
cprplot component-plus-residual plot
lvr2plot leverage-versus-squared-residual plot
rvfplot residual-versus-fitted plot
rvpplot residual-versus-predictor plot
-------------------------------------------------------------------------
The following standard postestimation commands are also available:
command description
-------------------------------------------------------------------------
estat AIC, BIC, VCE, and estimation sample summary
estimates cataloging estimation results
hausman Hausman's specification test
lincom point estimates, standard errors, testing, and
inference for linear combinations of coefficients
linktest link test for model specification
lrtest likelihood-ratio test
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
suest seemingly unrelated estimation
test Wald tests of simple and composite linear hypotheses
testnl Wald tests of nonlinear hypotheses
-------------------------------------------------------------------------
Special-interest postestimation commands
In addition to the common estat commands, estat hettest, estat imtest,
estat ovtest, estat szroeter, and estat vif are also available. dfbeta
is also available. The syntax for dfbeta and these estat commands is the
same as after regress; see [R] regress postestimation.
In addition to the standard syntax of test, test after anova has three
additionally allowed syntaxes; see below. test performs Wald tests of
expressions involving the coefficients of the underlying regression
model. Simple and composite linear hypotheses are possible.
Syntax for predict
predict after anova follows the same syntax as predict after regress and
can provide predictions, residuals, standardized residuals, studentized
residuals, the standard error of the residuals, the standard error of the
prediction, the diagonal elements of the projection (hat) matrix, and
Cook's D. See [R] regress postestimation for details.
Syntax for test after anova
In addition to the standard syntax of test, test after anova also allows
the following:
test, test(matname) [mtest[(opt)] matvlc(matname)] syntax a
test, showorder syntax b
test [term [term ...]] [/ term [term ...]] [, symbolic] syntax c
syntax a test expression involving the coefficients of the underlying
regression model; you provide information as a matrix
syntax b show underlying order of design matrix, which is useful when
constructing matname argument of the test() option
syntax c test effects and show symbolic forms
Menu
Statistics > Linear models and related > ANOVA/MANOVA > Test linear
hypotheses after anova
Options for test after anova
test(matname) is required with syntax a of test. The rows of matname
specify linear combinations of the underlying design matrix of the
ANOVA that are to be jointly tested. The columns correspond to the
underlying design matrix (including the constant if it has not been
suppressed). The column and row names of matname are ignored.
A listing of the constraints imposed by the test() option is
presented before the table containing the tests. You should examine
this table to verify that you have applied the linear combinations
you desired. Typing test, showorder allows you to examine the
ordering of the columns for the design matrix from the ANOVA.
mtest[(opt)] specifies that tests are performed for each condition
separately. opt specifies the method for adjusting p-values for
multiple testing. Valid values for opt are
bonferroni Bonferroni's method
holm Holm's method
sidak Sidak's method
noadjust no adjustment is to be made
Specifying mtest without an argument is equivalent to
mtest(noadjust).
matvlc(matname), a programmer's option, saves the variance-covariance
matrix of the linear combinations involved in the suite of tests.
For the test Lb = c, what is returned in matname is LVL', where V is
the estimated variance-covariance matrix of b.
showorder causes test to list the definition of each column in the design
matrix. showorder is not allowed with any other option.
symbolic requests the symbolic form of the test rather than the test
statistic. When this option is specified with no terms (test,
symbolic), the symbolic form of the estimable functions is displayed.
Examples
---------------------------------------------------------------------------
Setup
. webuse sewage
. anova particulate s / m|s / f|m|s / w|f|m|s /, dropemptycells
Test s with pooled m|s and f|m|s terms
. test s / m|s f|m|s
Test pooled m|s and f|m|s terms with w|f|m|s
. test m|s f|m|s / w|f|m|s
---------------------------------------------------------------------------
Setup
. webuse systolic
. anova systolic drug disease drug#disease
Symbolic form for the test of the main effect of drug
. test drug, symbolic
Test whether coefficient on first drug is equal to the coefficient on
second drug
. test 1.drug = 2.drug
Calculate linear prediction
. predict yhat
---------------------------------------------------------------------------
Also see
Manual: [R] anova postestimation
Help: [R] anova; [R] regress postestimation
