cholesterol {multcomp} | R Documentation |
Cholesterol reduction for five treatments; data set taken from Westfall et al. (1999, p. 153). All pairwise comparisons according to Tukey in a balanced one-way layout.
data(cholesterol)
This data frame contains the following variables
A
, B
, C
,
D
, E
See Westfall et al. (1999, p. 153)
P. H. Westfall, R. D. Tobias, D. Rom, R. D. Wolfinger, Y. Hochberg (1999). Multiple Comparisons and Multiple Tests Using the SAS System. Cary, NC: SAS Institute Inc.
data(cholesterol) # adjusted p-values for all-pairwise comparisons in a one-way layout # tests for restricted combinations simtest(response ~ trt, data=cholesterol, type="Tukey", ttype="logical") # adjusted p-values all-pairwise comparisons in a one-way layout # (tests for free combinations -> p-values will be larger) simtest(response ~ trt, data=cholesterol, type="Tukey", ttype="free") # enter now the estimates as parameters # begin with degrees of freedom nu <- as.integer(45) # estimates parm <- c(10.6151, -4.8331, -1.3901, 1.7597, 4.7461, 10.3325) # build the covariance matrix N <- rep(2, 5) contrast <- contrMat(N, type="Tukey") covm <- rep(-0.20254649, 36) covm <- matrix(covm, ncol=6) covm[1,2:6] <- rep(0.02893521, 5) covm[2:6,1] <- rep(0.02893521, 5) covm[1,1] <- 0.14467606 for (i in 2:6) { covm[i,i] <- 0.83912115 } # use the work-horse directly (and add zero column for the intercept) csimint(estpar=parm, df=nu, covm=covm, cmatrix=cbind(0, contrast)) csimtest(estpar=parm, df=nu, covm=covm, cmatrix=cbind(0, contrast), ttype="logical")