Skip to main content
ARS Home » Research » Publications at this Location » Publication #229742
Title: RISK ANALYSIS, ANALYSIS OF VARIANCE: GETTING MORE FROM OUR DATA

Author
item Clapham, William
item Fedders, James
item TEUTSCH, C - VIRGINIA TECH

Submitted to: Forage and Grazinglands
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 4/1/2009
Publication Date: 4/1/2009
Citation: Clapham, W.M., Fedders, J.M., Teutsch, C. 2009. RISK ANALYSIS, ANALYSIS OF VARIANCE: GETTING MORE FROM OUR DATA. Forage and Grazinglands. Available: http://www.plantmanagementnetwork.org/fg/element/sum2.aspx?id=7911.

Interpretive Summary: Statistical techniques such as Analysis of Variance and Regression Analysis are used routinely to analyze and interpret agricultural data from which recommendations are drawn. These techniques are suited to identify sources of variability, differences among treatments, and identify trends. However, determining differences among treatments does not always translate into determining which treatment has the highest probability of success. Risk analysis uses the same data set, but focuses on the mean, standard deviation and distribution. Using these factors, we can determine the probabilities for success or failure for different treatments given the objectives of the user. We conducted this study to demonstrate the utility in conducting risk analysis in conjunction with analysis of variance. We developed a synthetic data set to simplify the demonstration of the technique, followed by an analysis of a bermudagrass trial conducted over 5 years. Mean differences among cultivars were determined using analysis of variance, and risk analysis developed distributions for all cultivars from which cumulative probability curves were developed. Depending upon the yield objective, the probabilities for success or failure were determined easily. Farmers are gamblers and make large capital investments at the beginning of a growing season. Technology that is expressed in terms of probabilities of success or failure may have a better chance to be transferred.

Technical Abstract: Analysis of variance (ANOVA) and regression are common statistical techniques used to analyze agronomic experimental data and determine significant differences among yields due to treatments or other experimental factors. Risk analysis provides an alternate and complimentary examination of the same data by determining yield probabilities for each treatment or factor. We generated and analyzed a synthetic data set to illustrate that data with similar means, as determined by ANOVA, can have markedly different probability distributions due to differences in standard deviations. We then applied the techniques on data from a five-year yield trial of 13 Bermudagrass cultivars. ANOVA detected significant year by cultivar interactions while risk analysis illustrated differences among the cultivars in yield stability and in the probabilities of achieving specific yield goals. Together, ANOVA and risk analysis provide a more complete view of the data that facilitates technical transfer of experimental results to producers and other end-users.