𝔖 Bobbio Scriptorium
✦   LIBER   ✦

A Monte Carlo Study of Some Censored Data Wilcoxon Rank Tests

✍ Scribed by Marie-Louise Öhman

Publisher
John Wiley and Sons
Year
2007
Tongue
English
Weight
695 KB
Volume
32
Category
Article
ISSN
0323-3847

No coin nor oath required. For personal study only.

✦ Synopsis

Abstract

The variance estimators usually applied for the generalized censored data Wilcoxon rank tests by Gehan and Peto & Prentice, are heavily biased in unbalanced problems. This paper reports the results of a Monte Carlo simulation study, where jackknifing is used to construct estimators of variance. Size, power and variance properties are compared for five variance estimators, when using different combinations of group sizes, failure and censoring patterns. The variance estimators are the permutational, the conditional permutational and the jackknife variance estimators for the statistic of Gehan and the asymptotic and the jackknife variance estimators for the statistic of Peto & Prentice. It appears that observed size, power and variance properties may be improved by using the jackknife variance estimator, when comparing to the variance estimators usually applied.

📜 SIMILAR VOLUMES

Some preliminary results from a Monte Ca
Some preliminary results from a Monte Carlo study of a dilute aqueous solution of ethanol
✍ Giuliano Alagona; Alessandro Tani 📂 Article 📅 1982 🏛 Elsevier Science 🌐 English ⚖ 617 KB

Encrptu! rcsulk. solute-solvent and sohcnt-solvent radwl dulribullon I'~IICIIOIIS (rd8) obtamcd WIIII 3 SIOIIMCXIO (M. I'. T) simulation of an aqueous solution of ~rxwcthsnol Jre rcportcd. The solvauon oi the CIIJ md OHgroups or, similar to that of molccuk Ibc CH4 and HzO. whde the CHz is much more

A Monte Carlo Study to Evaluate the Perf
A Monte Carlo Study to Evaluate the Performance of Selected Tests of Homogeneity in Sparse Contingency Tables
✍ Prof. Dale F. Kraemer; Robert F. Woolson 📂 Article 📅 2007 🏛 John Wiley and Sons 🌐 English ⚖ 848 KB

We address the problem of tests of homogeneity in two-way contingency tablea in cam-control studies when the case category is subdivided into k subcategoriea. In this situation, we have two cells with large frequencies and 2 x k cells with frequencies that become small as k increaeee. We propose two

Comparison of Resubstitution, Data Split
Comparison of Resubstitution, Data Splitting, the Bootstrap, and the Jackknife as Methods for Estimating Validity Indices of New Marker Tests: A Monte Carlo Study
✍ Dr. U. Abel; J. Berger 📂 Article 📅 1986 🏛 John Wiley and Sons 🌐 English ⚖ 432 KB 👁 2 views

E s t i m a t q the diagnoetic efficienoy of marker t e & on the baain of the training eet is an intricate problem of discriminant analysis for which no analytical whtion exita. The paper outlines the problem. describee various popular entimation produrea and presenta the reeulta of computer nimulst

Testing for centre effects in multi-cent
Testing for centre effects in multi-centre survival studies: a Monte Carlo comparison of fixed and random effects tests
✍ Per Kragh Andersen; John P. Klein; Mei-Jie Zhang 📂 Article 📅 1999 🏛 John Wiley and Sons 🌐 English ⚖ 115 KB 👁 3 views

The problem of testing for a centre e!ect in multi-centre studies following a proportional hazards regression analysis is considered. Two approaches to the problem can be used. One "ts a proportional hazards model with a "xed covariate included for each centre (except one). The need for a centre spe

The performance of heteroskedasticity an
The performance of heteroskedasticity and autocorrelation robust tests: a Monte Carlo study with an application to the three-factor Fama–French asset-pricing model
✍ Surajit Ray; N. E. Savin 📂 Article 📅 2008 🏛 John Wiley and Sons 🌐 English ⚖ 147 KB 👁 1 views

## Abstract This paper illustrates the pitfalls of the conventional heteroskedasticity and autocorrelation robust (HAR) Wald test and the advantages of new HAR tests developed by Kiefer and Vogelsang in 2005 and by Phillips, Sun and Jin in 2003 and 2006. The illustrations use the 1993 Fama–French t