Accelerating the Pool-Adjacent-Violators Algorithm for Isotonic Distributional Regression.

IF 1 4区数学 Q3 STATISTICS & PROBABILITY

Methodology and Computing in Applied Probability Pub Date : 2022-01-01 DOI:10.1007/s11009-022-09937-2

Alexander Henzi, Alexandre Mösching, Lutz Dümbgen

引用次数: 11

Abstract

In the context of estimating stochastically ordered distribution functions, the pool-adjacent-violators algorithm (PAVA) can be modified such that the computation times are reduced substantially. This is achieved by studying the dependence of antitonic weighted least squares fits on the response vector to be approximated.

Abstract Image

查看原文本刊更多论文

加速等渗分布回归的池-邻接-违法者算法。

在估计随机有序分布函数的情况下，可以对池邻接违规者算法(PAVA)进行改进，从而大大减少了计算时间。这是通过研究反压加权最小二乘拟合对拟逼近响应向量的依赖来实现的。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Methodology and Computing in Applied Probability 数学-统计学与概率论

CiteScore

1.70

自引率

0.00%

发文量

审稿时长

6-12 weeks

期刊介绍： Methodology and Computing in Applied Probability will publish high quality research and review articles in the areas of applied probability that emphasize methodology and computing. Of special interest are articles in important areas of applications that include detailed case studies. Applied probability is a broad research area that is of interest to many scientists in diverse disciplines including: anthropology, biology, communication theory, economics, epidemiology, finance, linguistics, meteorology, operations research, psychology, quality control, reliability theory, sociology and statistics. The following alphabetical listing of topics of interest to the journal is not intended to be exclusive but to demonstrate the editorial policy of attracting papers which represent a broad range of interests: -Algorithms- Approximations- Asymptotic Approximations & Expansions- Combinatorial & Geometric Probability- Communication Networks- Extreme Value Theory- Finance- Image Analysis- Inequalities- Information Theory- Mathematical Physics- Molecular Biology- Monte Carlo Methods- Order Statistics- Queuing Theory- Reliability Theory- Stochastic Processes