asreml
and records the result in an asrtests.object.Tests for a single term, using a REML ratio test (REMLRT) for a random term or based
on Wald statistics for a fixed term. The term must be in the fitted model.
A random term is removed from the model fit and a REMLRT is
performed using REMLRT.asreml. It compares the fit of the model in
asreml.obj and the newly fitted model without the term.
If the newly fitted model is retained, any boundary terms are then removed
using rmboundary.asrtests.
For a fixed term, the probability of the Wald
statistics is extracted from the pseudo-anova table produced by
wald.asreml. If this is available in the asrtests.object, it is
used; otherwise wald.asreml is called to add it to the
asrtests.object. Whether nonsignificant terms are dropped is controlled
by drop.ran.ns for random terms and drop.fix.ns for fixed terms. A row is
added to the test.summary data.frame for the term that is tested.
# S3 method for asrtests
testranfix(asrtests.obj, term=NULL, alpha = 0.05,
allow.unconverged = TRUE, allow.fixedcorrelation = TRUE,
checkboundaryonly = FALSE,
drop.ran.ns = TRUE, positive.zero = FALSE,
bound.test.parameters = "none",
bound.exclusions = c("F","B","S","C"), REMLDF = NULL,
drop.fix.ns = FALSE, denDF="numeric", dDF.na = "none",
dDF.values = NULL, IClikelihood = "none",
trace = FALSE, update = TRUE,
set.terms = NULL, ignore.suffices = TRUE,
bounds = "P", initial.values = NA, ...)An asrtests.object containing the components (i) asreml.obj,
(ii) wald.tab, and (iii) test.summary.
If the term is not in the model, then the supplied asreml
object will be returned. Also, reml.test will have the likelihood
ratio and the p-value set to NA and the degrees of freedom to zero.
Similarly, the row of test.summary for the term will have
its name, DF set to NA, p-value set to NA, and action set to Absent.
An asrtests.object containing the components (i) asreml.obj,
(ii) wald.tab, and (iii) test.summary.
A single model term that is valid in asreml, stored
as a character. The names of fixed terms must match those in the wald.tab
component of the asrtests.obj, while the names of random terms must
match those in the vparameters component of the asreml.obj component
in the asrtests.obj.
The significance level for the test.
A logical indicating whether to accept a new model
even when it does not converge. If FALSE, it will be
checked whether convergence can be achieved with the removal of
any boundary random terms; random terms will be retested if terms
are removed. Also, if FALSE and the fit of the new model has
converged, but that of the old model has not, the new model will be
accepted.
A logical indicating whether to accept a new model
even when it contains correlations in the model whose values have been
designated as fixed, bound or singular. If FALSE and the new model
contains correlations whose values have not been able to be estimated,
the supplied asrtests.obj is returned. The fit in the
asreml.obj component of the supplied asrtests.obj will
also be tested and a warning issued if both fixed correlations are found
in it and allow.fixedcorrelation is FALSE.
If TRUE then boundary and singular terms are not removed by
rmboundary.asrtests; a warning is issued instead.
A logical indicating whether to drop a random
term from the model when it is nonsignificant. Note that
multiple terms specified using a single asreml::at function
will only be dropped as a whole. If the term was specified using
an asreml::at function with a single level, then it can be
removed and either the level itself or its numeric
position in the levels returned by the levels function
can be specified in term.
Indicates whether the hypothesized values for the
variance components being tested are on the boundary
of the parameter space. For example, this is true
for positively-constrained variance components that,
under the reduced model, are zero. This argument does
not need to be set if bound.test.parameters is set.
Indicates whether for the variance components
being tested, at least some of the hypothesized values
are on the boundary of the parameter space.
The possibilities are "none", "onlybound"
and "one-and-one". The default is "none",
although if it is set to "none" and
positive.zero is TRUE then
bound.test.parameters is taken to be "onlybound".
When bound.test.parameters is set to
"one-and-one", it signifies that there are two
parameters being tested, one of which is bound and the
other is not. For example, the latter is true for testing
a covariance and a positively-constrained variance component
that, under the reduced model, are zero.
A character specifying one or more bound (constraint) codes that
will result in a variance parameter being excluded from the count of
estimated variance parameters in using REMLRT.asreml.
If set to NULL then none will be excluded.
A numeric giving the difference in the number of variance parameters
whose estimates are not of the type specified in bound.exclusions
for two models being compared in a REML ratio test using
REMLRT.asreml. If NULL then this is determined from
the information in the asreml object for the two models.
A logical indicating whether to drop a fixed
term from the model when it is nonsignificant. Note that
multiple terms specified using a single asreml::at function
can only be dropped as a whole. If the term was specified using
an asreml::at function with a single level, then it can be
removed and either the level itself or its numeric
position in the levels returned by the levels function
can be specified.
Specifies the method to use in computing approximate denominator
degrees of freedom when wald.asreml is called. Can be none
to suppress the computations, numeric for numerical methods,
algebraic for algebraic methods or default, the default,
to autommatically choose numeric or algebraic computations depending
on problem size. The denominator degrees of freedom are calculated
according to Kenward and Roger (1997) for fixed terms in the dense
part of the model.
The method to use to obtain substitute denominator degrees of freedom.
when the numeric or algebraic methods produce an NA. If
dDF.na = "none", no subtitute denominator degrees of freedom
are employed; if dDF.na = "residual",
the residual degrees of freedom from asreml.obj$nedf are used;
if dDF.na = "maximum", the maximum of those denDF that are available,
excluding that for the Intercept, is used; if all denDF are NA,
asreml.obj$nedf is used. If dDF.na = "supplied",
a vector of values for the denominator degrees of freedom is to
be supplied in dDF.values. Any other setting is ignored and
a warning message produced. Generally, substituting these degrees of freedom is
anticonservative in that it is likely that the degrees of freedom used will be
too large.
A vector of values to be used when dDF.na = "supplied".
Its values will be used when denDF in a test for a fixed effect
is NA. This vector must be the same length as the number of
fixed terms, including (Intercept) whose value could be NA.
A character that controls both the occurence and the type
of likelihood for information criterion in the test.summary
of the new asrtests.object. If none, none are
included. Otherwise, if REML and family is set to
asr_guassian (the default), then the AIC and BIC based
on the Restricted Maximum Likelihood are included; if full
and family is set to asr_guassian,
then the AIC and BIC based on the full likelihood, evaluated using
REML estimates, are included. If family is asr_binomial
or asr_poisson, with dispersion set to 1, the
deviance is extracted from object and used to
calculate the AIC and BIC.
(See also infoCriteria.asreml.)
If TRUE then partial iteration details are displayed when ASReml-R functions are invoked; if FALSE then no output is displayed.
If TRUE, and set.terms is NULL, then
newfit.asreml is called to fit the model to be tested,
using the values of the variance parameters stored in
the asreml.object, that is stored in asrtests.obj, as starting values.
If FALSE or set.terms is not NULL, then
newfit.asreml will not use the stored variance parameter
values as starting values when fitting the new model, the only
modifications being (i) those for the supplied terms and
(ii) those specified via ....
A character vector specifying the terms that are to have
bounds and/or initial values set prior to fitting.
The names must match those in the vparameters component of the
asreml.obj component in the new asrtests.object.
A logical vector specifying whether the suffices of the
asreml-assigned names of the variance terms (i.e. the
information to the right of an "!", other than "R!") is to
be ignored in matching elements of terms.
If TRUE for an element of terms, the suffices
are stripped from the asreml-assigned names.
If FALSE for an element of terms, the element
must exactly match an asreml-assigned name for a
variance term. This vector must be of length one or the
same length as terms. If it is of length one then
the same action is applied to the asreml-assigned
suffices for all the terms in terms.
A character vector specifying the bounds to be applied
to the terms specified in set.terms. This vector
must be of length one or the same length as set.terms.
If it is of length one then the same constraint is
applied to all the terms in set.terms.
If any of the bounds are equal to NA then they are
left unchanged for those terms.
A character vector specifying the initial values for
the terms specified in terms. This vector
must be of length one or the same length as terms.
If it is of length one then the same initial value is
applied to all the terms in terms.
If any of the initial.values are equal to NA then they are
left unchanged for those terms.
Further arguments passed to asreml, wald.asreml and
as.asrtests.
Chris Brien
Kenward, M. G., & Roger, J. H. (1997). Small sample inference for fixed effects from restricted maximum likelihood. Biometrics, 53, 983-997.
asremlPlus-package, as.asrtests,
chooseModel.asrtests, REMLRT.asreml,
rmboundary.asrtests,
newfit.asreml, changeModelOnIC.asrtests,
changeTerms.asrtests, reparamSigDevn.asrtests
if (FALSE) {
data(Wheat.dat)
current.asr <- asreml(yield ~ Rep + WithinColPairs + Variety,
random = ~ Row + Column + units,
residual = ~ ar1(Row):ar1(Column),
data=Wheat.dat)
current.asrt <- as.asrtests(current.asr, NULL, NULL)
current.asrt <- rmboundary(current.asrt)
# Test nugget term
current.asrt <- testranfix(current.asrt, "units", positive=TRUE)
}Run the code above in your browser using DataLab