I have come across a dataset of time to event, which is highly skewed. Men and woman have the same median, but the really long times are only for men. One way to show this is the 90% percentile, but does anyone have a way to also show that there would be a significant difference in the 90% percentile?
Adrian Esterman
Stata will do it using their quantile regression procedure qreg. For example, if the time to event variable is called time, then you would use
qreg time sex, quantile (0.9)
Hope this helps
Adrian
0 votes
0 thanks
- Badges
- Science topic
- Similar topics
- Medicine
- Physiology
- Biosignals
- Biomedical Signal Processing
- Statistical Analysis
Similar questions and discussions