Survival.jl
Survival.jl copied to clipboard
JuliaStats
ENH: Add log rank testing
This PR adds log rank testing for comparing two or more fitted survival functions (fit with the Kaplan Meier estimator).
The unit tests are based on results from R and Stata.
Codecov Report
Merging #36 (4d40ac1) into master (755433a) will decrease coverage by
0.87%. The diff coverage is97.41%.
@@ Coverage Diff @@
## master #36 +/- ##
==========================================
- Coverage 99.54% 98.67% -0.88%
==========================================
Files 6 6
Lines 222 377 +155
==========================================
+ Hits 221 372 +151
- Misses 1 5 +4
| Impacted Files | Coverage Δ | |
|---|---|---|
| src/Survival.jl | 100.00% <ø> (ø) |
|
| src/kaplanmeier.jl | 97.59% <97.41%> (-2.41%) |
:arrow_down: |
Continue to review full report at Codecov.
Legend - Click here to learn more
Δ = absolute <relative> (impact),ø = not affected,? = missing dataPowered by Codecov. Last update 755433a...4d40ac1. Read the comment docs.
Great.
I definitely think Survival.jl should have log rank testing implemented.
We highly need this for Julia to be a viable option for doing statistics/bio-statistics.
Yes, for sure, adding the log-rank test to this package has been on my backlog of desired features since about 2017. 😄 Apologies, I should have spoken up on this PR sooner; I haven't been ignoring it. I have a number of internal changes planned that should be able to significantly simplify the implementation and I've finally gotten around to making some of them. Once that's in a good state I'll help adapt this PR accordingly. Thanks for the contribution and for your patience, @kshedden!
Great, thanks for the update. Also, it would be very useful to have an EntryTime field in the EventTime struct to be able to handle delayed entry/left truncation.
