asremlPlus (version 2.0-2)

testrcov.asrtests: Fits a new rcov formula using asreml and tests whether the change is significant.

Description

Fits a new rcov formula using asreml and tests whether the change is significant. If simpler = FALSE the model to be fitted must be more complex than the one whose fit has been stored in asrtests.obj. That is, the new model must have more parameters. However, if simpler = TRUE the model to be fitted must be simpler than the one whose fit has been stored in asrtests.obj in that it must have fewer parameters. Any boundary terms are removed using rmboundary.asrtests, which may mean that the models are not nested. The test is a REML likelihood ratio test that is performed using reml.lrt.asreml, which is only valid if the models are nested. It compares the newly fitted model with the fit of the model in asrtest.obj. A row is added to the test.summary data.frame using the supplied label.

Usage

testrcov.asrtests(terms=NULL, asrtests.obj, label = "R model", 
                  simpler = FALSE, alpha = 0.05, 
                  positive.zero = FALSE, denDF="default", 
                  update = TRUE, trace = FALSE,
                  set.terms = NULL, ignore.suffices = TRUE, 
                  constraints = "P", initial.values = NA, ...)

Arguments

terms

a model for the rcov argument in asreml, stored as a character.

asrtests.obj

an asrtests object for a fitted model that is a list containing an asreml object, a wald.tab data.frame with 4 columns, and a

label

a character string to use as the label in test.summary and which indicates what is being tested.

simpler

a logical indicating whether the new model to be fitted is simpler than the already fitted model whose fit is stored in asrtests.obj.

alpha

the significance level for the test.

positive.zero

a logical indicating whether the hypothesized values for the varaince components being tested are on the boundary of the parameter space. For example, this is be true for positively-c

denDF

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,

update

if TRUEthen update.asreml is called to fit the model with the rcov model supplied in terms. In doing this the arguments R.param and G.param are s

trace

if TRUE then partial iteration details are displayed when ASReml-R functions are invoked; if FALSE then no output is displayed.

set.terms

a character vector specifying the terms that are to have constraints and/or initial values set prior to fitting.

ignore.suffices

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 igno

constraints

a character vector specifying the constraints to be applied to the terms specified in terms. This vector must be of length one or the same length as terms. If it i

initial.values

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 leng

...

further arguments passed to asreml and to wald.asreml.

Value

• An asrtests object, which is a list containing:
  1. asreml.obj: anasremlobject containing the fit after thetermhas been omitted from the model;
  2. wald.tab: a 4-columndata.framecontaining a pseudo-anova table for the fixed terms produced bywald.asreml;
  3. test.summary: adata.framewith columnsterm,DF,denDF,pandaction. A row is added to it for each term that is dropped, added or tested or a note that several terms have been added or removed. A row contains the name of the term, the DF, the p-value and the action taken. Possible codes are:Dropped,Retained,Swapped,Unswapped,Significant,Nonsignificant,Absent,Added,RemovedandBoundary. If the changed model did not converge,Unconvergedwill be added to the code. Note that the logicalasreml.obj$convergealso reflects whether there is convergence.
  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, a p-value set to NA, and action set to Absent.

See Also

asremlPlus-package, asrtests, newrcov.asrtests, choose.model.asrtests, reml.lrt.asreml, rmboundary.asrtests, newfit.asreml, testswapran.asrtests, addrm.terms.asrtests, sig.devn.reparam.asrtests

Examples

data(Wheat.dat)
current.asr <- asreml(yield ~ Rep + WithinColPairs + Variety, 
                      random = ~ Row + Column + units,
                      rcov = ~ ar1(Row):ar1(Column), 
                      data=Wheat.dat)
current.asrt <- asrtests(current.asr, NULL, NULL)
current.asrt <- rmboundary.asrtests(current.asrt)
# Test Row autocorrelation
current.asrt <- testrcov.asrtests("~ Row:ar1(Column)", current.asrt, 
                                  label="Row autocorrelation", simpler=TRUE)
print(current.asrt)