On the Exact Distribution of Maximally Selected Rank Statistics

Science Direct Working Paper No S1574-0358(04)70152-5

26 Pages Posted: 5 Mar 2018

See all articles by Torsten Hothorn

Torsten Hothorn

University of Erlangen-Nürnberg

Berthold Lausen

affiliation not provided to SSRN

Date Written: February 2002

Abstract

The construction of simple classification rules is a frequent problem in medical research. For example a difference in overall survival time may suggest distinct types, i.e. subgroups of patients, of diffuse large B-cell lymphoma identified by gene expression profiling. Maximally selected rank statistics allow the evaluation of cutpoints, which provide the classification of different risk groups in a quantitative or ordered predictor variable. We discuss the computation of the exact distribution and we derive a new lower bound based on an extension of an algorithm for the exact distribution of a linear rank statistic. For small to moderate sample sizes and typical quantiles the lower bound of the exact distribution is a substantial improvement compared to approximations based on an improved Bonferroni inequality or based on the asymptotic Gaussian process. We use simulation results to compare our lower bound with the exact distribution. Our proposal is illustrated by two clinical studies: different prognosis for patients with diffuse large B-cell lymphoma based on gene expression profiling and the predicted value of the left ventricular ejection fraction for recurrence free survival of patients with malignant arrhythmias.

Keywords: Cutpoint selection, Small sample, Exact distribution of rank statistics, Ties, Censoring

Suggested Citation

Hothorn, Torsten and Lausen, Berthold, On the Exact Distribution of Maximally Selected Rank Statistics (February 2002). Science Direct Working Paper No S1574-0358(04)70152-5, Available at SSRN: https://ssrn.com/abstract=3133711

Torsten Hothorn (Contact Author)

University of Erlangen-Nürnberg ( email )

Schloßplatz 4
Erlangen, DE Bavaria 91054
Germany

Berthold Lausen

affiliation not provided to SSRN

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
244
Abstract Views
1,024
Rank
227,861
PlumX Metrics