Statistical methods for cosmological parameter selection and estimation

Abstract

The estimation of cosmological parameters from precision observables is an important industry with crucial ramifications for particle physics. In this article, I discuss the statistical methods presently used in cosmological data analysis, highlighting the main assumptions and uncertainties. The topics covered are parameter estimation, model selection, multimodel inference, and experimental design, all primarily from a Bayesian perspective. Copyright © 2009 by Annual Reviews. All rights reserved.