PROC ARIMA with binary response

Reply
New Contributor
Posts: 2

PROC ARIMA with binary response

Is it possible to combine a binary response variable (e.g. whether or not a patient is readmitted) with a time series model using PROC ARIMA?

Thanks!

Super User
Posts: 19,877

Re: PROC ARIMA with binary response

No idea, but it sounds more like survival analysis.

What doesn't survival analysis cover that you would want in ARIMA, some sort of seasonality?

New Contributor
Posts: 2

Re: PROC ARIMA with binary response

I'm interested in investigating the effect of an intervention on readmission rate, after controlling for patient-level covariates. I have about 3 years of historical/pre-intervention data and 1.5 years of post-intervention data. I want to incorporate time trend to account for changes in medical practice over time and its relation with readmission.

Respected Advisor
Posts: 2,655

Re: PROC ARIMA with binary response

That sounds, at least to me, more like a survival analysis with a time-dependent covariate, as proposed by @Reeza.  Think about what the ARIMA model would be fitting--a long string of zeroes, a single 1, perhaps some more 1's (if you model as still admitted), then another long string of zeroes.  That is not a good dataset for fitting an ARIMA model.  Instead, time to re-admission, with a covariate that describes the intervention status, strikes me as something that would work.  Check out PROC PHREG.

Steve Denham

Super User
Posts: 19,877

Re: PROC ARIMA with binary response

I would add some indicator variables, possible time dependent to account for the changes in practice.

You'll have to be careful with the pre-intervention/post-intervention data to make sure they're handled appropriately, but survival analysis is what you're looking for.

Respected Advisor
Posts: 2,655

Re: PROC ARIMA with binary response

, that's what I was trying to say.  I think a record would look like:

subjid      date      admission_status      intervention_status      covariate1      covariate2      (other covariates of interest).

That should set it up for a survival analysis, as per Example 67.7 Time-Dependent Repeated Measurements of a Covariate.

Steve Denham


Ask a Question
Discussion stats
  • 5 replies
  • 390 views
  • 0 likes
  • 3 in conversation