Indexat a

Llicència i ús

Citacions

Altmetrics

Anàlisi d'autories institucional

Compartir

Estimating odds and log odds with guaranteed accuracy

Publicat a:Statistical Papers. 66 (1): 26- - 2025-02-01 66(1), DOI: 10.1007/s00362-024-01639-w

Autors: Mendo, L

Afiliacions

Resum

Two sequential estimators are proposed for the odds p/(1-p)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$p/(1-p)$$\end{document} and log odds log(p/(1-p))\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\log (p/(1-p))$$\end{document} respectively, using independent Bernoulli random variables with parameter p as inputs. The estimators are unbiased, and guarantee that the variance of the estimation error divided by the true value of the odds, or the variance of the estimation error of the log odds, are less than a target value for any p is an element of(0,1)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$p \in (0,1)$$\end{document}. The estimators are close to optimal in the sense of Wolfowitz's bound.

Paraules clau