PostHocTest(x, ...)
## S3 method for class 'aov':
PostHocTest(x, which = NULL,
method = c("hsd","bonf","lsd","scheffe","newmankeuls"),
conf.level = 0.95, ordered = FALSE, ...)
## S3 method for class 'PostHocTest':
print(x, digits = getOption("digits"), ...)
## S3 method for class 'PostHocTest':
plot(x, ...)
"hsd"
, "bonf"
, "lsd"
, "scheffe"
, "newmankeuls"
, defining the method for the pairwise comparisons.TRUE
then the calculated differences in the means will all be positive. The signifTukeyHSD
, aov
, pairwise.t.test
,
ScheffeTest
PostHocTest(aov(breaks ~ tension, data = warpbreaks), method = "lsd")
PostHocTest(aov(breaks ~ tension, data = warpbreaks), method = "hsd")
PostHocTest(aov(breaks ~ tension, data = warpbreaks), method = "scheffe")
r.aov <- aov(breaks ~ tension, data = warpbreaks)
# compare p-values:
round(cbind(
lsd= PostHocTest(r.aov, method="lsd")$tension[,"pval"]
, bonf=PostHocTest(r.aov, method="bonf")$tension[,"pval"]
), 4)
# only p-values by setting conf.level to NA
PostHocTest(aov(breaks ~ tension, data = warpbreaks), method = "hsd",
conf.level=NA)
Run the code above in your browser using DataLab