Non-linear interrupted time series analysis: is it possible?

[Richard Lu]

Hi all,

Does anyone know of a method to perform an interrupted time series analysis whereby the pre- or post-intervention regression is non-linear with respect to time? For instance, the outcome variable spikes at the intervention, but then slowly attenuates to a stable value over time.

Best,
Richard

[Phil Bromiley]

You didn't get a quick answer. You'll increase your chances of a helpful answer by following the FAQ on asking questions - provide Stata code in code deimiters, Stata output, and sample data using dataex. Also, try to reduce the code you include to what is needed to demonstrate your problem. You should also have searched for the major terms in your question from the command window of Stata (findit majorterm) and in the subject index in the documentation (under index at the bottom of the list of documentation).

If you know where the intervention is, you could use dummy variables and non-linear functions of the x's (e.g., x squared) to generate this functional form.