Premium
Reduction of Total Sample Size and Cost of Sampling in Tests of Hypothesis by Using Unequal Group Sizes
Author(s) -
Trajstman A. C.
Publication year - 1992
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/bimj.4710340113
Subject(s) - sample size determination , statistics , mathematics , sample (material) , reduction (mathematics) , sampling (signal processing) , group (periodic table) , econometrics , computer science , chemistry , physics , thermodynamics , geometry , organic chemistry , filter (signal processing) , computer vision
The standard approach in calculating the appropriate sample size required to detect a specified difference in the means of two populations for given type I and II errors assumes equal sample sizes in each group. It is shown here that equal sample sizes are usually sub‐optimal with respect to total sample size and with respect to total cost of the experiment. This is may be important in experiments involving animals when costs are measured not only in monetary terms but also in terms of animal suffering or inconvenience.