Can I exclude Insignificant Covariates from Cox Model?

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

I am using the Cox regression model to forecast failures of machines. I have several possible covariates. I ran the analysis in SPSS. The method I used to add covariates was backward stepwise (Wald). The table 'Variables in the Equation' shows that some covariates are not significant.Can I exclude the insignificant variable, rerun the Cox regression?

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：significant covariates covariate Variates Variate machines backward possible question solution

The baseline hazard is usually estimated by the more straightforward Breslow or Kalbfleisch-Prentice methods

It is not statistically correct to remove "insignificant" variables, just as stepwise regression (without penalization) is invalid. Much has been written about this topic.

How exactly are you creating forecasts from this model? Are you using smoothing spline estimates of the Schoenfeld residuals to estimate the baseline hazard function? If so, do you do this before or after eliminating "insignificant" variables? If your goal is prediction, some very prognostic markers may have inference on hazards ratios which are not significant