Rich, apparently it's a method of computing statistics. Here's an excerpt from a site I found:
Intuitive Biostatistics: Comparing Two Survival Curves
"... It is common to compare two survival curves, to compare two treatments. Compare two survival curves using the log-rank test. This test calculates a P value testing the null hypothesis that the survival curves are identical in the two populations. If that assumption is true, the P value is the probability of randomly selecting subjects whose survival curves are as different (or more so) than was actually observed. (You will sometimes see survival curves compared with the method of Mantel-Haenszel, rather than the log-rank test. The two methods are essentially equivalent.)..."
|