rsq | R Documentation |
coxph
or survfit
modelr^2 measures for a a coxph
or survfit
model
rsq(x, ...) ## S3 method for class 'coxph' rsq(x, ..., sigD = 2) ## S3 method for class 'survfit' rsq(x, ..., sigD = 2)
x |
A |
... |
Additional arguments (not implemented). |
sigD |
significant digits (for ease of display).
If |
A list
with the following elements:
cod |
The coefficient of determination, which is R^2 = 1-exp((2/n).(L[0]-L[1])) where L[0] and L[1] are the log partial likelihoods for the null and full models respectively and n is the number of observations in the data set. |
mer |
The measure of explained randomness, which is: R^2[mer] = 1-exp((2/m).(L[0]-L[1])) where m is the number of observed events. |
mev |
The measure of explained variation (similar to that for linear regression), which is: R^2 = R^2[mer] / ( R^2[mer] + pi/6(1-R^2[mer]) ) |
Nagelkerke NJD, 1991. A Note on a General Definition of the Coefficient of Determination. Biometrika 78(3):691–92. http://www.jstor.org/stable/2337038 JSTOR
O'Quigley J, Xu R, Stare J, 2005. Explained randomness in proportional hazards models. Stat Med 24(3):479–89. http://dx.doi.org/10.1002/sim.1946 Wiley (paywall) http://www.math.ucsd.edu/~rxu/igain2.pdf UCSD (free)
Royston P, 2006. Explained variation for survival models. The Stata Journal 6(1):83–96. http://www.stata-journal.com/sjpdf.html?articlenum=st0098
data("kidney", package="KMsurv") c1 <- coxph(Surv(time=time, event=delta) ~ type, data=kidney) cbind(rsq(c1), rsq(c1, sigD=NULL))
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.