I do not believe that there is a rule of thumb regarding the proportion of censored cases for a survival analysis - plenty of medical research papers publish survival analyses with as little as 10 percent of their cohort having reached the primary endpoint. However, a few things that stand out to me from your description:
1) You will probably start your analysis by producing Kaplan-Meier curves to illustrate the survival in your ethnic groups. You should make sure to display the N remaining within each group along the bottom of your Figure so the reader can place the estimates in proper context.
2) From there, I expect that you will create a Cox proportional-hazards model with the ethnic groups as your primary predictor variable of interest, and then possibly adjust for potential confounding variables (age at diagnosis, stage of cancer, tumor size, etc). There is one (very, very loose) rule of thumb in multivariate modeling tends to be no more than one variable/parameter in your model for every 10 "events" - so with only 35 known events, you're likely to be very limited in the number of covariates that you may consider. If you are testing for differences between ethnic groups and wish to adjust for age, cancer stage, etc...you're going to run out of room for additional parameters very quickly, so you should carefully choose with confounding variables to include (or if they are even necessary at all - for example, if distribution of "age at diagnosis" is nearly identical in the different ethnic groups, you may choose to omit that from your model, as it should not confound the relationship between ethnic group and survival).
3) You do not mention how many ethnic groups you are considering or the proportion of patients within each group, but this is one cause for concern that I see...for example, suppose that one of your ethnic groups of interest includes only 20 patients, with 3 deaths. It will be very hard to know whether there is a true difference in survival between that ethnic group versus the other ethnic groups within your study population, particularly if you attempt to adjust for confounding variables. The term "power" gets thrown around recklessly far too much, but this would be a case where even if there was/is a true difference in survival between that group and the remainder of your cohort, you are likely insufficiently powered to determine whether that differences is likely to be real.
Finally, I will slightly redirect a statement of Colleen's from above: I don't think it's of tremendous concern that the authors cannot estimate a "median survival" (although I will share a humorous anecdote with you here - I have previously worked with a group of surgeons that wished to estimate "median" survival in a large cohort of patients when far less than 50 percent of their patients had died, and they just absolutely could not understand why it was impractical to estimate the median survival. It was like trying to explain that 2+2=4 to people that just kept asking "But why isn't it 5?"). Sure, it would be nice to state that the median survival in (Group A) is significantly different from the median survival in (Group B), but as noted above, many papers all around the medical literature use survival analyses with far less than half of their cohort meeting the primary endpoint. However, Colleen's statement does get at the point that with so few of your patients having reached the endpoint, it is likely that even if there ARE differences in survival between ethnic groups, you may not have sufficient data to determine that. You run the risk of performing this analysis and showing a "non-significant" result even if there is an elevated risk in one ethnic group vs. the others simply because you have so few events, so make sure to interpret your findings in proper context.
------------------------------
Andrew D. Althouse, PhD
Supervisor of Statistical Projects
UPMC Heart & Vascular Institute
Presbyterian Hospital, Office C701
Phone: 412-802-6811
Email:
althousead@upmc.edu
Original Message:
Sent: 02-24-2016 01:41
From: Colleen Kelly
Subject: Survival Analysis. Proportion of Censored Cases.
In general, you should worry about 93% censored observations. If all of these patients were censored at follow-up time X (say 1 year), then you would not have much information in the data, and would not be able to calculate the median survival, for example. All you would know is that the median is greater than 1 year. But, the amount of information in your data will depend on the distribution of the "date of last contact". If the length of follow-up varies widely over patients, you will have more information than the simple example above.
--