A method for determining the optimum transform for covariates of the cox model with application to 3680 cases of intraocular melanoma

✍ Scribed by John W. Gamel; Ian W. McLean

• Publisher: Elsevier Science
• Year: 1988
• Tongue: English
• Weight: 416 KB
• Volume: 21
• Category: Article
• ISSN: 0010-4809
• DOI: 10.1016/0010-4809(88)90005-5

✦ Synopsis

For most applications of the Cox Model, a simple exponential relationship is assumed between covariates of this model and relative force of mortality (A). A method has been developed to examine this relationship in detail for data sets that contain a sufficient number of deaths. This method was applied to 3680 cases of intraocular melanoma with 1178 deaths over 20 years of follow-up, using largest tumor dimension (LTD) as a predictor of tumorrelated death. Results indicated that the transform A = exp# log Lrn} provides a closer approximation to observed mortality for this data set than the more traditional A = exp {P&n}. Additional applications to mathematically generated data sets revealed a close correspondence between A estimated by this method and the A programmed into each data Set.