compareC {compareC} | R Documentation |
This is a function used to test if the difference in two correlated overall C indices is statistically significant
compareC(timeX, statusX, scoreY, scoreZ)
timeX |
The vector of actual survival time X, one survival time for each observation |
statusX |
The matching vector of event indicator for time X, 1 if occured and 0 otherwise |
scoreY |
The vector of the first measured biomarker or score Y, one for each of the same observations |
scoreZ |
The vector of the second measured biomarker or score Z, one for each of the same observations |
est.c |
The estimated two C indices |
est.diff_c |
The estimated difference of the two C indices, i.e., |
est.vardiff_c |
The estimated variance of the difference of two C indices |
est.varCxy |
The estimated variance of the C index for scoreY |
est.varCxz |
The estimated variance of the C index for scoreZ |
est.cov |
The estimated covariance between the two C indices for scoreY and that for scoreZ |
zscore |
Z score (test statistic) for hypothesis testing |
pval |
P value for the comparison of two C indices |
Under non-random censoring, the returned p-value is statistically invalid as the assumption of random censoring is violated.
Le Kang, Weijie Chen
Harrell FE, Califf RM, Pryor DB, Lee KL, and Rosati RA. (1982) Evaluating the yield of medical tests. The Journal of the American Medical Association, 247(18), 2543–2546
Pencina MJ and D'Agostino RB. (2004) Overall C as a measure of discrimination in survival analysis: model specific population value and confidence interval estimation. Statistics in Medicine, 23(13), 2109–2123
Kang L, Chen W, Petrick NA, and Gallas BD. (2014) Comparing two correlated C indices with right-censored survival outcome: a one-shot nonparametric approach. Statistics in Medicine, 34(4), 685–703, doi: 10.1002/sim.6370
demo(testC)