Timeline for Survival analysis with only censored event times?
Current License: CC BY-SA 4.0
17 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 21, 2023 at 7:53 | history | edited | whatbehaviour | CC BY-SA 4.0 | added 248 characters in body |
| Apr 21, 2023 at 7:33 | history | edited | whatbehaviour | CC BY-SA 4.0 | Added information. |
| Apr 21, 2023 at 7:24 | comment | added | whatbehaviour | The title change makes sense, and I'll add the requested information. There are, as usual, predictors to include in the modelling :) | |
| Apr 21, 2023 at 7:22 | vote | accept | whatbehaviour | ||
| Apr 7, 2023 at 17:47 | comment | added | EdM | I changed the title to say "censored event times" instead of "censored events," based on the comments from @Alexis. Change back if you feel that's incorrect. Also, in terms of the best modeling strategy, are you just interested in modeling a single set of fish, or is there some intervention for which you want to compare outcomes or covariates whose associations with outcome you want to evaluate? Please add that information by editing the question, as comments are easy to overlook and can be deleted. | |
| Apr 7, 2023 at 17:44 | history | edited | EdM | CC BY-SA 4.0 | Made title more specific |
| Apr 6, 2023 at 18:18 | comment | added | EdM | @Alexis if an event is observed at $t=2$ in this situation, then the time to the event can be considered "left censored" with an upper limit of 2 for the time to event. Or, if you know that time starts at time=0, you can consider it "interval censored" between 0 and 2. The word "censored" is correct, but it would have been better to say "censored event times" rather than "censored events." | |
| Apr 6, 2023 at 18:03 | comment | added | Alexis | @EdM I mean, suppose in a unit in the group measured at the second time it is observed that the event occurred: we do not know if the event had occurred by $t=1$ or after $t=1$ but before $t=2$. Is this what you mean by time to event is censored? Also: The OP uses "censored" in the title, and that is specifically what my comments have been trying to clarify. | |
| Apr 6, 2023 at 17:01 | comment | added | EdM | @Alexis the remaining $1-p$ of the sample after $t=1$ provides no information about event times, because there is no yes/no event/none observation on them yet. In that sense the "censoring" terminology doesn't really apply to one of that group at all until the time of examination for presence of the event. | |
| Apr 6, 2023 at 16:29 | comment | added | Alexis | Thank you @EdM Ok, let me make sure I am following: because measurement is destructive for a given proportion $p$ measured at $t=1$, even though we certainly have a measure of "did event occur by $t=1$ for for the first $p$ of the sample", the remaining $1-p$ portion's time to event is censored for $t=1$ since they have not yet been observed? Am I understanding that? | |
| Apr 6, 2023 at 14:26 | comment | added | EdM | @Alexis what's censored is the time to an event, not the individual with the event. That's an important distinction here. If an event is observed at dissection, the time to the event only has a known upper limit. That's a left-censored observation time. Its contribution to likelihood differs from that of an exact time. In this design, times to observed events are necessarily left censored while the times to events for individuals without events are right censored. See the miceData in the R icenReg package for an example. | |
| Apr 5, 2023 at 18:59 | comment | added | Alexis | The title seems misleading to me: if events occurred for some units, then I would not label them right censored which I am accustomed to mean "unit left the study without the event occurring". Am I understanding you correctly? | |
| Apr 5, 2023 at 18:11 | comment | added | Ben | I believe this is an example of "current status" data. | |
| Apr 5, 2023 at 18:04 | answer | added | Björn | timeline score: 3 | |
| Apr 5, 2023 at 17:35 | answer | added | AdamO | timeline score: 3 | |
| Apr 5, 2023 at 16:04 | answer | added | EdM | timeline score: 5 | |
| Apr 4, 2023 at 13:33 | history | asked | whatbehaviour | CC BY-SA 4.0 |