Hi everyone! It is my first post in this forum.
The question that has taken my sleep is about survival analysis.
I have to make a survival analysis plot. It is easy when one thinks of a final event, such as dead. It is complete, unquestionable, and irreversible.
However, I usually work in ophthalmology studies. Sometimes, I have to follow eyes concerning the intraocular pressure (IOP). Let's suppose I define the limit of IOP of 20 mmHg, and the failure is the pressure above this limit. Suppose I follow the IOP every week, for example, week 1 = 18, week 2 = 18, week 3 = 19, then week 4 = 23 mmHg. The patient reaches failure in week 4.
There is a more difficult condition: what if the patient has the IOP such as 18 / 18 / 23 / 15 / 21 / 25 / 16???
In this case, the patient reaches failure in the third observation, but in the next (15), he or she entered the normal range. Then, it comes to the failure criteria again, and finally, in the last observation (16), joined the normal range!!! How can I make a survival plot in this case? Is it possible to consider these "chunks" of time when it is in the normal range? I appreciate any help from you. Have a lovely weekend!
Related Posts with Survival analysis when the failure may be "reached again"
Dummy Variables OmmittedIn a study looking at the effect of foreign ownership, we have run into the issue that our variables…
aweight, pweight or fweight? What to use for WLS?Dear all, I would like to apply a weighted least squares model but I do not know which weight to us…
How to make a hbar which shows percentage of sum of one variable over groupsI have a dataset like this (part of it): Code: * Example generated by -dataex-. To install: ssc in…
How to plot differences in means for diff-in-diff common trend (from Bleakeley & Chin (2004))Dear Stata community, This is my first post on the forum. I'm struggling to recreate figure 1 from …
Save t-statistic output for all observations (function statsby)Hi all, I would like to save all the t-statistics as output for all of my regression observations u…
Subscribe to:
Post Comments (Atom)
0 Response to Survival analysis when the failure may be "reached again"
Post a Comment