A Bayes rule for the symmetric multiple comparisons problem.
waller(K, q, f, Fc)
| K | Is the loss ratio between type I and type II error |
|---|---|
| q | Numerator Degrees of freedom |
| f | Denominator Degrees of freedom |
| Fc | F ratio from an analysis of variance |
Waller value for the Waller and Duncan test.
K-RATIO (K): value specifies the Type 1/Type 2 error seriousness ratio for the Waller-Duncan test. Reasonable values for KRATIO are 50, 100, and 500, which roughly correspond for the two-level case to ALPHA levels of 0.1, 0.05, and 0.01. By default, the procedure uses the default value of 100.
Waller, R. A. and Duncan, D. B. (1969). A Bayes Rule for the Symmetric Multiple Comparison Problem, Journal of the American Statistical Association 64, pages 1484-1504.
Waller, R. A. and Kemp, K. E. (1976) Computations of Bayesian t-Values for Multiple Comparisons, Journal of Statistical Computation and Simulation, 75, pages 169-172.
Principles and procedures of statistics a biometrical approach Steel & Torry & Dickey. Third Edition 1997.
# Table Duncan-Waller K=100, F=1.2 pag 649 Steel & Torry library(agricolae) K<-100 Fc<-1.2 q<-c(8,10,12,14,16,20,40,100) f<-c(seq(4,20,2),24,30,40,60,120) n<-length(q) m<-length(f) W.D <-rep(0,n*m) dim(W.D)<-c(n,m) for (i in 1:n) { for (j in 1:m) { W.D[i,j]<-waller(K, q[i], f[j], Fc) }} W.D<-round(W.D,2) dimnames(W.D)<-list(q,f) print(W.D)#> 4 6 8 10 12 14 16 18 20 24 30 40 60 120 #> 8 2.85 2.91 2.94 2.96 2.97 2.98 2.99 2.99 2.99 3.00 3.00 3.00 3.00 3.00 #> 10 2.85 2.93 2.98 3.01 3.04 3.05 3.06 3.07 3.08 3.09 3.10 3.10 3.11 3.12 #> 12 2.85 2.95 3.01 3.05 3.08 3.10 3.12 3.13 3.14 3.16 3.17 3.19 3.20 3.21 #> 14 2.85 2.96 3.03 3.08 3.12 3.14 3.16 3.18 3.19 3.21 3.23 3.25 3.27 3.29 #> 16 2.85 2.97 3.05 3.11 3.15 3.18 3.20 3.22 3.24 3.26 3.29 3.31 3.34 3.36 #> 20 2.85 2.99 3.08 3.14 3.19 3.23 3.26 3.28 3.30 3.33 3.37 3.40 3.44 3.47 #> 40 2.85 3.02 3.13 3.22 3.29 3.35 3.39 3.43 3.47 3.52 3.58 3.64 3.72 3.79 #> 100 2.85 3.04 3.17 3.28 3.36 3.44 3.50 3.55 3.59 3.67 3.76 3.86 3.98 4.11