Missing covariate data within cancer prognostic studies: A review of current reporting and proposed guidelines

Research output: Contribution to journalArticle


Colleges, School and Institutes


Prognostic models play a crucial role in the clinical decision-making process. Unfortunately, missing covariate data impede the construction of valid and reliable models, potentially introducing bias, if handled inappropriately. The extent of missing covariate data within reported cancer prognostic studies, the current handling and the quality of reporting this missing covariate data are unknown. Therefore, a review was conducted of 100 articles reporting multivariate survival analyses to assess potential prognostic factors, published within seven cancer journals in 2002. Missing covariate data is a common occurrence in studies performing multivariate survival analyses, being apparent in 81 of the 100 articles reviewed. The percentage of eligible cases with complete data was obtainable in 39 articles, and was


Original languageEnglish
Pages (from-to)4-8
Number of pages5
JournalBritish Journal of Cancer
Early online date8 Jun 2004
Publication statusPublished - 8 Jun 2004