Timeline for What is the minimum sample size for kaplan meier
Current License: CC BY-SA 3.0
11 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 21, 2018 at 12:56 | comment | added | Frank Harrell | My book goes into that. It's based on controlling the chance that the maximum absolute difference with the true survival curve, over time, is less than some value. | |
| Jul 20, 2018 at 22:18 | comment | added | Khashir | @FrankHarrell: Sorry, I meant about the last part—the 184 subjects minimum? | |
| Jul 19, 2018 at 1:00 | comment | added | Frank Harrell | rdocumentation.org/packages/Hmisc/versions/4.1-1/topics/cpower and its references | |
| Jul 18, 2018 at 22:04 | comment | added | Khashir | @FrankHarrell: Thanks for the answer—do you have a source, to offer more context/explanation? | |
| May 25, 2016 at 2:16 | comment | added | Frank Harrell |
Then cpower will help you. It will allow you to compute the power to detect any given hazard ratio if you can estimate the proportion surviving a fixed time t. Or you can look into the code inside cpower to see how you can do this just given the total number of events. Or you can solve for the survival estimate in the control group that gives you a certain total number of events, by trial and error with cpower.
|
|
| May 24, 2016 at 13:02 | comment | added | user1288515 | So my question would be, if a reviewer came to you and said "you did this kaplan meier analysis, but you have not many individuals in the data set, how can you be sure that the data set was big enough for the log rank test to accurately calculate survival differences between two groups when you say that the difference in survival is statistically significant between two groups"? This is the question that I am trying to anticipate; and come up with a calculation/software that I can use to answer this. I appreciate your help. | |
| May 24, 2016 at 13:01 | comment | added | user1288515 | Thank you. I should not be focussing on the expected values to decide if the dataset is big enough. I apologise that I sound confused, I'm a biologist.I did a survival analysis using different genotypes, but I want to make sure my test is statistically accurate, and there is enough data for the test to give "real" results... | |
| May 24, 2016 at 12:14 | comment | added | Frank Harrell |
The expected number of events would require every subject to have the same follow-up time unless you use a parametric model, and would require a minimum of 96 subjects. Estimation of the expected number of events is not the goal of the log rank test. But sometimes for study planning (as with cpower and spower functions in R Hmisc) we estimate event probabilities at a fixed time using published or historical data to plug into the power calculations/simulations.
|
|
| May 24, 2016 at 9:34 | comment | added | user1288515 | ....But I'm not sure this is suitable, since the aim is not to "allow estimation of the expected number of events in the two groups". Would you know of a way to statistically calculate whether the log rank test has enough power? The example of code I put up is just an extremely small example to illustrate my point, I do have other data sets with more data. | |
| May 24, 2016 at 9:34 | comment | added | user1288515 | Thank you, I understand. Re:power of the 2-sample log rank test. I have heard that one way I could work out if my logrank test is valid is to do a "power calculation". I have found a VERY basic example of such a calculation: statstodo.com/SSizSurvival_Pgm.php (the section: Single calculation; power estimation). I assume that in the example, the survival rate for group 1 is the final survival rate. I looked for a similar program, in R/python. I came across your cpower in Hmisc.... | |
| May 23, 2016 at 13:19 | history | answered | Frank Harrell | CC BY-SA 3.0 |