Yahoo Answers is shutting down on May 4th, 2021 (Eastern Time) and beginning April 20th, 2021 (Eastern Time) the Yahoo Answers website will be in read-only mode. There will be no changes to other Yahoo properties or services, or your Yahoo account. You can find more information about the Yahoo Answers shutdown and how to download your data on this help page.
Trending News
what type of statistical test should I use to analyse a single variable over successive years?
I want to analyse the number of hospital admissions for a number of years prior to and following a given event to see if that event had an impact.
I would also like to control for age of admission if you could give me some insight as to how I would go about doing that.
I expect to see a gradual change occur over time following the event, therefore it doesnt make sense to group the data and compare the means.
1 Answer
- az_lenderLv 75 years ago
With the keep-it-simple-stupid philosophy, you could simply ask whether the mean number of admissions per year before the event differs significantly from the mean number of admissions per year after the event. If there aren't enough years to make sense out of that question, try the mean number of admissions per month. Do a two-sample "t" test, using the sample standard deviations of these numbers as a basis for calculating a pooled estimate of the standard deviation, and hence, a standard error for the difference of the two means.
"Control for age of admission" -- you could, for example, simply ignore all persons admitted who are under (over?) a specific age. Another approach to the whole thing would be to compare the mean ages for the last 100 persons admitted before the event, vs. the first 100 persons admitted after the event. Or something like that.
