| sort.alldiffs {asremlPlus} | R Documentation |
Sorts the components in an alldiffs.object according to the predicted values
associated with a factor.
Description
Sorts the rows of the components in an alldiffs.object
(see as.alldiffs) that are data.frames and the rows and columns
of those that are matrices according to the predicted values in the
predictions component. These predicted values are generally obtained using
predict.asreml by specifying a classify term comprised of one or
more variables. Generally, the values associated with one variable are sorted in
parallel within each combination of values of the other variables. When there is more
than one variable in the classify term, the sorting is controlled using
one or more of sortFactor, sortParallelToCombo and sortOrder.
If there is only one variable in the classify then all components are sorted
according to the order of the complete set of predictions.
Note that renewClassify.alldiffs is called after sorting to ensure that
the order of the rows and columns of the components is in standard order for the new
variable order.
Usage
## S3 method for class 'alldiffs'
sort(x, decreasing = FALSE, classify = NULL, sortFactor = NULL,
sortParallelToCombo = NULL, sortNestingFactor = NULL,
sortOrder = NULL, ...)Arguments
x |
An |
decreasing |
A |
classify |
A |
sortFactor |
A |
sortParallelToCombo |
A |
sortNestingFactor |
A |
sortOrder |
A The following creates a |
... |
further arguments passed to or from other methods. Not used at present. |
Details
The basic technique is to change the order of the levels of the sortFactor
within the predictions and, if present, backtransforms components so
that they are ordered for a subset of predicted values, one for each levels of the
sortFactor. When the classify term consists of more than one
variable then a subset of one combination of the values of variables other than
the sortFactor, the sortParallelToCombo combination, must be chosen for determining the
order of the sortFactor levels. Then the sorting of the rows (and columns)
will be in parallel within each combination of the values of sortParallelToCombo variables:
the classify term, excluding the sortFactor.
Value
The alldiffs.object supplied with the following components,
if present, sorted: predictions, vcov, backtransforms, differences,
p.differences and sed. Also, the sortFactor and sortOrder
attributes are set.
Author(s)
Chris Brien
See Also
as.alldiffs, allDifferences.data.frame,
print.alldiffs,
sort.predictions.frame, renewClassify.alldiffs,
redoErrorIntervals.alldiffs,
recalcLSD.alldiffs,
predictPlus.asreml, predictPresent.asreml
Examples
##Halve WaterRunoff data to reduce time to execute
data(WaterRunoff.dat)
tmp <- subset(WaterRunoff.dat, Date == "05-18")
##Use asreml to get predictions and associated statistics
## Not run:
#Analyse pH
m1.asr <- asreml(fixed = pH ~ Benches + (Sources * (Type + Species)),
random = ~ Benches:MainPlots,
keep.order=TRUE, data= tmp)
current.asrt <- as.asrtests(m1.asr, NULL, NULL)
current.asrt <- as.asrtests(m1.asr)
current.asrt <- rmboundary(current.asrt)
m1.asr <- current.asrt$asreml.obj
#Get predictions and associated statistics
TS.diffs <- predictPlus.asreml(classify = "Sources:Type",
asreml.obj = m1.asr, tables = "none",
wald.tab = current.asrt$wald.tab,
present = c("Type","Species","Sources"))
#Use sort.alldiffs and save order for use with other response variables
TS.diffs.sort <- sort(TS.diffs, sortFactor = "Sources",
sortParallelToCombo = list(Type = "Control"))
sort.order <- attr(TS.diffs.sort, which = "sortOrder")
#Analyse Turbidity
m2.asr <- asreml(fixed = Turbidity ~ Benches + (Sources * (Type + Species)),
random = ~ Benches:MainPlots,
keep.order=TRUE, data= tmp)
current.asrt <- as.asrtests(m2.asr)
#Use pH sort.order to sort Turbidity alldiffs object
diffs2.sort <- predictPlus(m2.asr, classify = "Sources:Type",
pairwise = FALSE, error.intervals = "Stand",
tables = "none", present = c("Type","Species","Sources"),
sortFactor = "Sources",
sortOrder = sort.order)
## End(Not run)
## Use lmeTest and emmmeans to get predictions and associated statistics
if (requireNamespace("lmerTest", quietly = TRUE) &
requireNamespace("emmeans", quietly = TRUE))
{
#Analyse pH
m1.lmer <- lmerTest::lmer(pH ~ Benches + (Sources * (Type + Species)) +
(1|Benches:MainPlots),
data=na.omit(tmp))
TS.emm <- emmeans::emmeans(m1.lmer, specs = ~ Sources:Type)
TS.preds <- summary(TS.emm)
den.df <- min(TS.preds$df, na.rm = TRUE)
## Modify TS.preds to be compatible with a predictions.frame
TS.preds <- as.predictions.frame(TS.preds, predictions = "emmean",
se = "SE", interval.type = "CI",
interval.names = c("lower.CL", "upper.CL"))
## Form an all.diffs object and check its validity
TS.vcov <- vcov(TS.emm)
TS.diffs <- allDifferences(predictions = TS.preds,
classify = "Sources:Type",
vcov = TS.vcov, tdf = den.df)
validAlldiffs(TS.diffs)
#Use sort.alldiffs and save order for use with other response variables
TS.diffs.sort <- sort(TS.diffs, sortFactor = "Sources",
sortParallelToCombo = list(Type = "Control"))
sort.order <- attr(TS.diffs.sort, which = "sortOrder")
#Analyse Turbidity
m2.lmer <- lmerTest::lmer(Turbidity ~ Benches + (Sources * (Type + Species)) +
(1|Benches:MainPlots),
data=na.omit(tmp))
TS.emm <- emmeans::emmeans(m2.lmer, specs = ~ Sources:Type)
TS.preds <- summary(TS.emm)
den.df <- min(TS.preds$df, na.rm = TRUE)
## Modify TS.preds to be compatible with a predictions.frame
TS.preds <- as.predictions.frame(TS.preds, predictions = "emmean",
se = "SE", interval.type = "CI",
interval.names = c("lower.CL", "upper.CL"))
## Form an all.diffs object, sorting it using the pH sort.order and check its validity
TS.vcov <- vcov(TS.emm)
TS.diffs2.sort <- allDifferences(predictions = TS.preds,
classify = "Sources:Type",
vcov = TS.vcov, tdf = den.df,
sortFactor = "Sources",
sortOrder = sort.order)
validAlldiffs(TS.diffs2.sort)
}