Genetic algorithms and their statistical applications: An introduction

Genetic algorithms (GA) are stochastic optimization tools that work on ''Darwinian'' models of population biology and are capable of solving for near-optimal solution for multivariable functions without the usual mathematical requirements of strict continuity, differentiability, convexity and other properties. The algorithm begins by choosing a large number of candidate solutions which propagate themselves through a ''selection criteria'' and are changed by the application of well-developed genetic operators. GAs are applied to problems in statistical estimation and the results are compared to the output of standard software. It is argued that many statistical and mathematical restrictions that usually restrict modeling and analysis can be dispensed with by employing the GA as an optimization technique. The use of GAs for solving discrete optimization problems with applications in statistics for the variable selection problem in regression and other multivariate statistical methods are also discussed.