Say one has the fatality and survivor rates of a pathogen in terms of geographical location (e.g., the latest data on the MERS-CoV).

France                      2 (1)
Italy                       3 (0)
Jordan                      2 (2)
Qatar                       2 (0)
Saudi Arabia               49 (32)
Tunisia                     2 (0)
United Kingdom (UK)         3 (2)
United Arab Emirates (UAE)  1 (1)
Total                      64 (38)

The total fatality rate is ~59%. However, I am not sure that this is a good measure: the rate for Saudi Arabia is ~65%, while the smaller cases have rates of 0 to 100%.

My thoughts are that the size of the outbreak should weight the outbreak's impact on the overall rate. However, I don't think averaging the individual rates would be correct. Is there a more appropriate measure that would allow me to take the size of the outbreak into account when calculating the overall impact?


Average proportions and the overall rate provide slightly different information but both can be interesting. There is nothing “incorrect” about computing a fatality rate for all known cases (this is know as the case fatality rate and is often computed per outbreak of a disease). The only thing is that you should not expect to find one “true” rate that would answer all your questions. Any number you might come up with would not necessarily represent the chance of survival of any one infected patient (depending on access to treatment, health system, etc.)

In any case, in this example, there is no reason to think anything of the difference between 59% and 65%. With only about 60 cases, you are nowhere near the level of precision needed to make that kind of distinction. You should really think of this number as “apparently more than half”, “high but not 90%” or “between 50 and 70%”.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.