Search Dictionary



Version history

  • Current: Jun 30, 2021

Log-rank test

The log-rank test is a nonparametric statistical test that compares the risk of death over time in two groups. This test is commonly used to compare two survival curves because it accommodates censored observations, which is usually included in biomedical data.

The survival data is often represented by plotting a Kaplan-Meier curve [Public domain image]. Also see Kaplan-Meier plot and Log-rank test by R and Survival test in R-training course.


Kaplan-Meier curve

Definitions in the literature

  • Log-rank test accommodates censored observations and compares the risk of death over time in the two groups [1].
  • The log-rank test is perhaps the most commonly used nonparametric method for comparing two survival curves and yields maximum power under proportional hazards alternatives [2].