Author
RICHARDSON, C. - TEXAS TECH | |
NUNNERY, G. - TEXAS TECH | |
WESTER, D. - TEXAS TECH | |
Cole, Noel | |
GALYEAN, M. - TEXAS TECH |
Submitted to: Journal of Animal Science Supplement
Publication Type: Peer Reviewed Journal Publication Acceptance Date: 10/8/2003 Publication Date: 6/1/2004 Citation: Richardson, C.R., Nunnery, G.A., Wester, D.B., Cole, N.A., Galyean, M.L. 2004. Power of test considerations for beef cattle experiments: a review. Journal of Animal Science Supplement. 82(E. Suppl.):E214-E222. Interpretive Summary: In biological experiments, statistical methods are routinely used to compare treatments and to develop a level of "certainty" on differences in treatments. For statistics to work best, an adequate experimental design and sample size are required. Beef cattle nutritional experiments are challenging to analyze because they differ from other animal experimentation in several ways including: l) dissimilar research facilities; 2) variation in types of pens; 3) use of individual animal data and metabolism studies; 4) seasonal effects by region; and 5) variation in the performance of control groups among locations due to differences in diet composition and animal genetics. This paper reviews methods to make use of power tests in the design of beef cattle experiments. The use of power tests in the planning and designing of beef cattle experiments provides information on sample sizes necessary to detect a treatment difference at a predetermined confidence level. Retrospective analysis of power provides additional information for researchers about previous experiments that may be helpful in designing subsequent investigations. However, care must be taken in interpretation of results of prospective and retrospective power analyses. Retrospective power analyses were determined on 80 experiments. Results indicated that retrospective power in beef cattle experiments is affected by design type, sample size, and the response variable measured Technical Abstract: The use of power tests in the planning and design of beef cattle experiments provides critical information on sample sizes necessary to detect a treatment difference at a predetermined significance (alpha) level. Post hoc (retrospective) analysis of power provides additional information for researchers about previous experiments that may be helpful in designing subsequent investigations. Nonetheless, care should be taken not to misinterpret the comparative results of prospective and retrospective power analyses because the former infers a value for the population, and the latter is an estimate based on a sample of the population. Benefits of prospective and retrospective power analyses in beef cattle experiments are similar to those for other species; however, because of differences in the methods and conditions involved, considerations for the use of power test procedures are specific for beef cattle research. Major differences include: l) dissimilar research facilities; 2) variation in types of pens (totally or partially enclosed indoor pens, open outdoor pens, enclosed fields, or open ranges); 3) use of individual animal data and metabolism studies; 4) seasonal effects by region on animals housed outside; and 5) variation in the performance of control groups among locations because of differences in diet composition and animal genetics. Retrospective power analyses were determined on 78 published experiments, and on two unpublished experiments. Experiments were compiled into categories that represented group (or pen) feeding, individual feeding, and metabolism studies. Estimated power in pen feeding experiments using randomized block designs (RBD,n = 30) was less than 0.80 for ADG and feed efficiency (FE), but not different from 0.80 for completely random designs (CRD, n = 4). Furthermore, estimated power was less for ADG than for FE in both design types. For individual feeding experiments using RBD (n = 4), power was not different from 0.80 for either ADG or FE; however, for CRD (n = 18), power was less than 0.80 for both ADG and FE. Power was similar for ADG and FE for both RBD and CRD in individual feeding experiments. In metabolism experiments, estimated power for nitrogen retention was less than 0.80 for Latin square designs (n = 20) but not for CRD (n = 4). Comparisons of power between experimental design types were likely influenced by the number of experiments involved. These data indicate that retrospective power in beef cattle experiments is affected by design type, sample size, and response variable measured. |