Statistical Methods in Astronomy

Abstract

We present a review of data types and statistical methods often encountered in astronomy. The aim is to provide an introduction to statistical applications in astronomy for statisticians and computer scientists. We highlight the complex, often hierarchical, nature of many astronomy inference problems and advocate for cross-disciplinary collaborations to address these challenges.1 ©AAS. Reproduced with permission. See [6] (doi:10.1088/0004-6256/150/5/150) for original publication.2 See

Astrophysical S-factors, Thermonuclear Rates, and Electron Screening Potential for the 3He(d,p)4He Big Bang Reaction via a Hierarchical Bayesian Model

“…The underlying idea is to decompose higherdimensional problems into a number of probabilistically linked lower-dimensional substructures. Hierarchical Bayesian models allow for a consistent inclusion of different types of uncertainties into the model, thereby solving inferential problems that are not amenable to traditional statistics (e.g., Gelman & Hill 2006;Parent & Rivot 2012;Loredo 2013;Long & de Souza 2018).…”

Astronomical observations: a guide for allied researchers

“…The references in this article include a mix of technical papers and lesstechnical descriptive works. Shorter introductions to astronomical observations, data and statistics are given by [29,33]. Comprehensive technical introductions to astronomical observations are found in several recent textbooks [12,45,50].…”

“…Comparison of observations with theoretical predictions often points to situations where physical understanding is inadequate, or judgment about the relevant areas of physics is incomplete. Because astronomy is an observational science with the conditions of observation largely out of the observer's control, consideration of selection bias and other effects in statistical inference is very important [33].…”

A Dependent Lindeberg Central Limit Theorem for Cluster Functionals on Stationary Random Fields

“…On the other hand, in some applications, only very little data are relevant to the estimates, not to mention that the estimates are also hidden among a large mass of "raw data". We can refer the reader to Davis and Mikosch [1] for examples in extremes and to Long and De Sousa [2] for examples in astronomy. This leads us to think of clusters of data deemed "relevant" (or extremal type, within the framework of extreme value theory), where we say that two relevant values belong to two different clusters if they belong to two different blocks.…”