Bootstrap study of parameter estimates for nonlinear Richards growth model through genetic algorithm

Abstract

Richards nonlinear growth model, which is a generalization of the well-known logistic and Gompertz models, generally provides a realistic description of many phenomena. However, this model is very rarely used as it is extremely difficult to fit it by employing nonlinear estimation procedures. To this end, utility of using a very powerful optimization technique of genetic algorithm is advocated. Parametric bootstrap methodology is then used to obtain standard errors of the estimates. Subsequently, bootstrap confidence-intervals are constructed by two methods, viz. the Percentile method, and Bias-corrected and accelerated method. The methodology is illustrated by applying it to India's total annual foodgrain production time-series data.