Class | Analysis and data manipulation command |
Name | surv |
Arguments | <age-at-onset> <censor> [<covariate1> [..<covariateN>]]. |
Carries out the log-rank nonparametric test for equality of survival curves across the different strata formed by crossclassifying one or more covariates. The variable censor is the binary outcome trait, which is affected when age-at-onset represents the time at which the individual first expressed the trait.
If no covariate is specified, tests each active marker in turn, carrying out a gene-dropping test of significance.
Example:
>> include adex.in >> surv onset ad apoe ------------------------------------------------------ Nonparametric survival analysis of trait "onset" ------------------------------------------------------ "ad" is outcome (censoring) trait. Covariates: apoe Number of strata = 5 Number of distinct times = 51 ad apoe N Obs Exp Var Z ---------- -------------------------------------------------- 2/3 8 1 2.35 2.09 -0.93 2/4 6 1 3.00 2.54 -1.26 3/3 64 7 18.69 9.49 -3.79 3/4 61 23 13.82 8.65 3.12 4/4 23 11 5.14 4.16 2.87 Log-rank Chi-square= 24.93 df= 4 (P=5e-5) >> surv onset ad Marker Nobs NAff Chi-square Asy P Emp P Iters -------------- ------ ------ ---------- ------ ------ ------ apoe 162 43 24.9 5e-5 0.0199 201 Surv ***
<< (lifetable) | Up to index | >> (gpe) |