|
Size: 1604
Comment:
|
Size: 2057
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 7: | Line 7: |
| Power = $$2 \Phi(\sqrt{np(1-p)hr^text{2}}-z_text{a/2})-1$$ | Power = $$2 \Phi(\sqrt{dp(1-p)hr^text{2}}-z_text{a/2})-1$$ |
| Line 9: | Line 9: |
| where ''n'' is the total sample size, ''p'' the probability of occurrence of the event in the population, ''hr'' the hazard ratio, ''a'' the two-sided type I error, $$\Phi$$ the inverse normal function and ''z'' the Standard Normal (or probit) function. | where ''d'' is the total number of events, ''p'' the probability of occurrence of the event in the population, ''hr'' the hazard ratio, ''a'' the two-sided type I error, $$\Phi$$ the inverse normal function and ''z'' the Standard Normal (or probit) function. |
| Line 13: | Line 13: |
| d = $$\frac{(z_text{1-a} + z_text{1-b})^text{2}}{\sigma^text{2}\hr^text{2}} | d = $$\frac{(z_text{a/2} + z_text{b/2})^text{2}}{\sigma^text{2}\log(hr)^text{2}} |
| Line 15: | Line 15: |
| dc = $$\frac{dc}{1-R^text{2}}$$ where $$R^text{2}$$ is the squared multiple correlation regression one covaraite on the others. | with $$\sigma^text{2}$$ equal to the variance of the covariate. dc = $$\frac{dc}{1-R^text{2}}$$ where $$R^text{2}$$ is the squared multiple correlation regression of the covariate of interest with the others in the case of more than one continuous covariate. This method is computed using this [attachment:powcoxc.xls spreadsheet.] This approach is similar to Hsieh's approach to computing power in logistic regression (see [:FAQ/power/llogPow:here].) This method may also be computed using the powerEpiCont function in R as illustrated [:FAQ/power/hazNR: here]. |
| Line 19: | Line 23: |
| Collett, D (2003) Modelling Survival Data in Medical Research Second Edition. Chapman and Hall:London | Collett, D (2003) Modelling Survival Data in Medical Research. Second Edition. Chapman and Hall:London |
Survival analysis power calculations
Power may be evaluated for comparing hazard rates (per unit time) using this [attachment:coxpow.xls spreadsheet] which uses a simple formula taken from Collett (2003) [http://stats.stackexchange.com/questions/7508/power-analysis-for-survival-analysis illustrated here] corresponding to a group regression estimate (ratio of hazards) in a Cox regression model. Alternatively the effect size can be expressed in terms of ratios of group survival rates as used by the power calculator given [http://www.stattools.net/SSizSurvival_Pgm.php here.]
Rearranging the equation given in Collett(2003)
Power = $$2 \Phi(\sqrt{dp(1-p)hr^text{2}}-z_text{a/2})-1$$
where d is the total number of events, p the probability of occurrence of the event in the population, hr the hazard ratio, a the two-sided type I error, $$\Phi$$ the inverse normal function and z the Standard Normal (or probit) function.
Hsieh and Lavori (2000) give sample size formulae for the number of deaths using continuous covariates in the Cox regression.
d = $$\frac{(z_text{a/2} + z_text{b/2})text{2}}{\sigmatext{2}\log(hr)^text{2}}
with $$\sigma^text{2}$$ equal to the variance of the covariate.
dc = $$\frac{dc}{1-Rtext{2}}$$ where $$Rtext{2}$$ is the squared multiple correlation regression of the covariate of interest with the others in the case of more than one continuous covariate. This method is computed using this [attachment:powcoxc.xls spreadsheet.]
This approach is similar to Hsieh's approach to computing power in logistic regression (see [:FAQ/power/llogPow:here].) This method may also be computed using the powerEpiCont function in R as illustrated [:FAQ/power/hazNR: here].
References
Collett, D (2003) Modelling Survival Data in Medical Research. Second Edition. Chapman and Hall:London
Hsieh FY and Lavori PW (2000) Sample size calculations for the Cox proportional hazards regression models with nonbinary covariates Controlled Clinical Trials 21 552-560.