COXREG results using PROC POWER

mostater — Fri, 02 Feb 2018 22:32:36 GMT

I am hoping someone can point out the error of my ways. I am trying to understand why greater power is achieved by increasing the assumed standard deviation of the predictor variable as in the example below:

proc power;

coxreg

hazardratio = 1.4

rsquare = 0.15

stddev = 1.2 2.4

ntotal = 80

eventprob = 0.8

power = .

;

run;

(This code was taken from the example provided in SAS documentation.)

Why would power be greater for a predictor that has greater variability? It seems like it should have the opposite effect...that the power should decrease.

The POWER Procedure

Cox Score Test in Proportional Hazards Regression

Fixed Scenario Elements

Method Hsieh-Lavori normal approximation

Probability of Event 0.8

R-square of Predictors 0.15

Test Hazard Ratio 1.4

Total Sample Size 80

Number of Sides 2

Alpha 0.05

Computed Power

Std

Index Dev Power

1 1.2 0.846

2 2.4 >.999

Re: COXREG results using PROC POWER

mostater — Wed, 07 Mar 2018 22:30:24 GMT

Bump...

Re: COXREG results using PROC POWER

cminard — Thu, 15 Nov 2018 17:55:32 GMT

Please see the following paper:
Hsieh, F. Y., and Lavori, P. W. (2000). “Sample-Size Calculations for the Cox Proportional Hazards Regression Model with Nonbinary Covariates.” Controlled Clinical Trials 21:552–560.

In this paper, the authors state the following:
"In a regression model, the variance of the estimate b₁ of the parameter θ₁ is inversely related to the variance of the corresponding covariate X₁."

Therefore, the variance of the parameter estimate would get smaller as the variance of the covariate increases.

I have not yet worked through the reasoning behind this argument though.

topic Re: COXREG results using PROC POWER in Statistical Procedures

COXREG results using PROC POWER

Re: COXREG results using PROC POWER

Re: COXREG results using PROC POWER