Log Rank Test in R-Survival Curve Comparison

Log Rank Test in R, the most frequent technique to compare survival curves between two groups is to use a log-rank test.

Test hypotheses:

Ho: In terms of survivability, there is no difference between the two groups.

Hi: There is a survival differential between the two groups.

We can reject the null hypothesis and infer that there is enough evidence to claim there is a difference in survival between the two groups if the p-value of the test is less than 0.05 (95% confidence level).

LSTM Network in R » Recurrent Neural network »

In R, we can use the survdiff() function from the survival package to do a log-rank test, which has the following syntax:

survdiff(Surv(time, status) ~ predictors, data)

The Chi-Squared test statistic and related p-value are returned by the above function

log-rank test in R.

Following libraries are required for the analysis.

library("survival")
library("survminer")
library("Rcpp")

The lung cancer data was utilized from the survival package.

Linear optimization using R » Optimal Solution »

data("lung")
head(lung)
    inst time status age sex ph.ecog ph.karno pat.karno meal.cal wt.loss
1    3  306      2  74   1       1       90       100     1175      NA
2    3  455      2  68   1       0       90        90     1225      15
3    3 1010      1  56   1       0       90        90       NA      15
4    5  210      2  57   1       1       90        60     1150      11
5    1  883      2  60   1       0      100        90       NA       0
6   12 1022      1  74   1       1       50        80      513       0

Type the following code to compute survival curves:

fit <- survfit(Surv(time, status) ~ sex, data = lung)
print(fit)
Call: survfit(formula = Surv(time, status) ~ sex, data = lung)
        n events median 0.95LCL 0.95UCL
sex=1 138    112    270     212     310
sex=2  90     53    426     348     550

The sort summary table can be accessed based on the below code

Linear Discriminant Analysis in R » LDA Prediction »

summary(fit)$table
records n.max n.start events   *rmean *se(rmean) median 0.95LCL 0.95UCL
sex=1     138   138     138    112 325.0663   22.59845    270     212     310
sex=2      90    90      90     53 458.2757   33.78530    426     348     550

Visulization

The following code allows us to understand the survival curves in a better way.

ggsurvplot(fit,
           pval = TRUE, conf.int = TRUE,
           risk.table = TRUE, # Add risk table
           risk.table.col = "strata", # Change risk table color by groups
           linetype = "strata", # Change line type by groups
           surv.median.line = "hv", # Specify median survival
           ggtheme = theme_bw(), # Change ggplot2 theme
           palette = c("#E7B800", "#2E9FDF"))

The survival chance is 1.0 at time zero (or 100 percent of the participants are alive).

At time 250, the chances of survival for sex=1 are about 0.55 (or 55 percent) and 0.75 (or 75 percent) for sex=2.

The median survival time for sex=1 is 270 days and for sex=2 is 426 days, indicating that sex=2 has a better survival rate than sex=1.

The following code shows how to perform a log-rank test to determine if there is a difference in survival between sex who received different treatments:

Decision Trees in R » Classification & Regression »

Perform log-rank test

surv_diff <- survdiff(Surv(time, status) ~ sex, data = lung)
surv_diff
Call:
survdiff(formula = Surv(time, status) ~ sex, data = lung)
        N Observed Expected (O-E)^2/E (O-E)^2/V
sex=1 138      112     91.6      4.55      10.3
sex=2  90       53     73.4      5.68      10.3
Chisq= 10.3  on 1 degrees of freedom, p= 0.001

The Chi-Squared test statistic is 10.3 with 1 degree of freedom and the corresponding p-value is 0.001. Since this p-value is less than 0.05, we reject the null hypothesis.

In other words, we have sufficient evidence to say that there is a statistically significant difference in survival between the two groups.

GK on Physics Questions-Part 3 » PSC Mock Test

You may also like...

Leave a Reply

Your email address will not be published. Required fields are marked *

4 + 20 =

Ads Blocker Image Powered by Code Help Pro

Quality articles need supporters. Will you be one?

You currently have an Ad Blocker on.

Please support FINNSTATS.COM by disabling these ads blocker.

Powered By
100% Free SEO Tools - Tool Kits PRO
Available for Amazon Prime