Recursive Parameter Estimation: Convergence

TL;DR

This paper investigates recursive estimation methods, where each estimate is iteratively refined from the previous one, and analyzes their convergence properties within general statistical models.

Contribution

It introduces a broad class of recursive estimators and provides theoretical results on their convergence behavior.

Findings

Proposes a general framework for recursive estimation procedures.

Establishes convergence conditions for the proposed estimators.

Applies the theory to various statistical models.

Abstract

We consider estimation procedures which are recursive in the sense that each successive estimator is obtained from the previous one by a simple adjustment. We propose a wide class of recursive estimation procedures for the general statistical model and study convergence.