# Statistical and Computational Tradeoff in Genetic Algorithm-Based Estimation

## TL;DR

This paper investigates the balance between statistical accuracy and computational effort when using genetic algorithms for estimation, highlighting how sampling variability and algorithm stochasticity interact under resource constraints.

## Contribution

It introduces a framework to analyze the tradeoff between statistical variability and computational cost in genetic algorithm-based estimation problems.

## Key findings

- Decomposition of estimation variability into sampling and algorithm stochasticity.
- Simulation results illustrating the tradeoff under resource constraints.
- Guidelines for balancing statistical accuracy and computational resources.

## Abstract

When a Genetic Algorithm (GA), or a stochastic algorithm in general, is employed in a statistical problem, the obtained result is affected by both variability due to sampling, that refers to the fact that only a sample is observed, and variability due to the stochastic elements of the algorithm. This topic can be easily set in a framework of statistical and computational tradeoff question, crucial in recent problems, for which statisticians must carefully set statistical and computational part of the analysis, taking account of some resource or time constraints. In the present work we analyze estimation problems tackled by GAs, for which variability of estimates can be decomposed in the two sources of variability, considering some constraints in the form of cost functions, related to both data acquisition and runtime of the algorithm. Simulation studies will be presented to discuss the statistical and computational tradeoff question.