Use of Box‐Cox Transformation Technique for Fitting Crop Yield Trends

Abstract

There is a need for a more general approach to selecting appropriate models for transformation of long‐term crop yield data prior to statistical analysis without a priori restrictions about the mathematical form of the model. A least restrictive formulation about the functional specification of a model is less likely to lead to erroneous results. The objective of the study is to illustrate a general approach to model selection via application of the Box‐Cox transformation technique to estimate national yield trends for corn (Zea mays L.), wheat (Triticum aestivum L.), and soybean [Glycine max (L.) Merr.] during the period 1960‐1979. Results suggest that corn and wheat yields were approaching a plateau level whereas soybeans showed no indication of levelling off of yields.

The Box-Cox Transformation Technique: A Review

“…2 • This was further generalized by Boylan et al (1982). Lin & Huang (1983)estimated the generalized functional form for the yield trend of wheat, corn and soybean. Newman (1977) estimated the relationship between the incidence of malaria and the mortality rate and concluded that the functional specificiation obtained by using the Box-Cox procedure was superior to earlier specifications.…”