A score test for assessing the cured proportion in the long-term survivor mixture model

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

9 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)3454-3466
Journal / PublicationStatistics in Medicine
Volume28
Issue number27
Publication statusPublished - 30 Nov 2009

Abstract

The long-term survivor mixture model is commonly applied to analyse survival data when some individuals may never experience the failure event of interest. A score test is presented to assess whether the cured proportion is significant to justify the long-term survivor mixture model. Sampling distribution and power of the test statistic are evaluated by simulation studies. The results confirm that the proposed test statistic performs well in finite sample situations. The test procedure is illustrated using a breast cancer survival data set and the clustered multivariate failure times from a multi-centre clinical trial of carcinoma. Copyright © 2009 John Wiley & Sons, Ltd.

Research Area(s)

  • Cured proportion, Long-term survivors, Mixture model, Random effects, Score test

Citation Format(s)

A score test for assessing the cured proportion in the long-term survivor mixture model. / Zhao, Yun; Lee, Andy H.; Yau, Kelvin K. W.; Burke, Valerie; McLachlan, Geoffrey J.

In: Statistics in Medicine, Vol. 28, No. 27, 30.11.2009, p. 3454-3466.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review