Sample Size for Selecting the Best Treatment in a Normal Response (Indifference-Zone)
Source:R/ss_best_normal.R
ss_best_normal.RdCalculates the minimum common sample size per group needed to achieve a specified probability (power) of correctly selecting the best group using the indifference-zone approach. This method assumes normally distributed responses with a known and common standard deviation.
Arguments
- power
Numeric. Desired probability of correctly selecting the best group.
- dif
Numeric. Indifferent-zone. Minimum difference that is considered meaningful.
- sd
Numeric. Common standard deviation of the response variable.
- ngroups
Integer. Number of groups (treatments) being compared.
- seed
Optional. Integer seed to use in the internal call to
multz().
Details
The indifference-zone approach guarantees that the probability of correct selection
is at least power, assuming the best group's mean exceeds the others by at
least dif. The calculation is based on Bechhofer's Procedure Nb.
Note
The function uses the quantile function multz(), which computes critical values
for the selection procedure. This implementation assumes equal variances and independent samples.