aovremm {RcmdrPlugin.TeachStat} | R Documentation |
ANOVA with random effects using the Moments method.
Description
Print the ANOVA table with random effects and compute the classical point estimations of the variance components using the Moments method.
Usage
aovremm(formula, data = NULL, ...)
Arguments
formula |
A formula specifying the model. |
data |
A data frame in which the variables specified in the |
... |
Arguments to be passed to other functions. |
Value
A list
See Also
Examples
##---- Should be DIRECTLY executable !! ----
##-- ==> Define data, use random,
##-- or do help(data=index) for the standard data sets.
## The function is currently defined as
function (formula, data = NULL, ...)
{
ANOV <- aov(formula, data, ...)
.ANOV <- summary(ANOV)
cat("-------------------------------")
cat("\n", gettext("ANOVA table", domain = "R-RcmdrPlugin.TeachStat"),
":\n", sep = "")
print(.ANOV)
cat("\n-------------------------------\n\n")
.sighat2 <- .ANOV[[1]]$`Mean Sq`[2]
.vars <- all.vars(formula)
.groups <- data[[.vars[2]]][!is.na(data[[.vars[1]]])]
.n <- length(.groups)
.ni <- table(.groups)
.c <- (.n^2 - sum(.ni^2))/(.n * (length(.ni) - 1))
.sighatalph2 <- (.ANOV[[1]]$`Mean Sq`[1] - .sighat2)/.c
if (.sighatalph2 < 0)
warning("Estimation of any variance component is not positive. The variance
component model is inadequate.")
.prop <- .sighatalph2/(.sighatalph2 + .sighat2)
estim <- c(.sighat2, .sighatalph2, .prop)
names(estim) <- c("var (Error)", "var (Effect)", "% var (Effect)")
cat("\n", gettext("Components of Variance", domain = "R-RcmdrPlugin.TeachStat"),
":\n", sep = "")
print(estim)
return(invisible(list(model = ANOV, estimation = estim)))
}
[Package RcmdrPlugin.TeachStat version 1.1.3 Index]