Experimental design, power and sample size for animal reproduction experiments
Phillip L. Chapman A C and George E. Seidel, Jr. BA Department of Statistics, Colorado State University, Fort Collins, CO 80523, USA.
B Animal Reproduction and Biotechnology Laboratory, Colorado State University, Fort Collins, CO 80523, USA.
C Corresponding author. Email: phillip.chapman@colostate.edu
Reproduction, Fertility and Development 20(1) 33-44 https://doi.org/10.1071/RD07183
Published: 12 December 2007
Abstract
The present paper concerns statistical issues in the design of animal reproduction experiments, with emphasis on the problems of sample size determination and power calculations. We include examples and non-technical discussions aimed at helping researchers avoid serious errors that may invalidate or seriously impair the validity of conclusions from experiments. Screen shots from interactive power calculation programs and basic SAS power calculation programs are presented to aid in understanding statistical power and computing power in some common experimental situations. Practical issues that are common to most statistical design problems are briefly discussed. These include one-sided hypothesis tests, power level criteria, equality of within-group variances, transformations of response variables to achieve variance equality, optimal specification of treatment group sizes, ‘post hoc’ power analysis and arguments for the increased use of confidence intervals in place of hypothesis tests.
Cornfield, J. , and Tukey, J. W. (1956). Average values of mean squares in factorials. Ann. Math. Statist. 27, 907–949.
