I am familiar with using regression with ARIMA errors to model interrupted time-series, in order to estimate the change in magnitude caused by a policy intervention. These models seem to be designed for a single time series, and thus if multiple time-series are analysed a model must be fit separately for each time-series.

I am interested in analysing the national impact of a policy intervention, the implementation of which was staggered in time across all (eight Australian) states. I can see three possible analysis approaches here:

  1. Fit a separate ARIMA model for each state
  2. Attempt to fit an aggregate national model, perhaps with one dummy variable indicating partial implementation and another indicating complete implementation
  3. Find a different model that works explictly on panel data. This would hopefully bring some kind of compromise between the no-pooling approach 1 and the complete pooling approach 2.

What sort of approach would you recommend here?


I would identify the true date of the intervention i.e. when it was fully realized for each state separately using Intervention Detection schemes. The true date (de facto) can often be different from the "known date" (de jure) because of either a pre or a post effect (delay). With a common ARIMA model and one composite intervention variable constructed from the de facto dates, I would then globally estimate all parameters ie. the ARIMA coefficients and the national impact. The coefficient for the composite Intervention Variable would then reflect the national effect. When conducting this Global estimation you need to ensure that the prediction/fitted value for the first reading in the second state is not affected by the latest readings for the first state. For example if the ARIMA model is an AR(12) the first 12 expectations for each state would be the 12 observed values thus generating 12 zero errors. Commercial software with this built-in feature is rare but available.

  • 1
    $\begingroup$ Thanks for your response Irish. I have read a number of your responses re: intervention detection and am becoming increasingly convinced. One thing I am a little unclear about is whether you are suggesting a multiple state approach (i.e. approach 1) or an aggregate national approach (i.e. approach 2), or simply to try both. Could you clarify that please? $\endgroup$ – fmark Nov 21 '11 at 22:31
  • $\begingroup$ :fmark What I had in mind is a case where you lock in a suitable ARIMA MODEL , based upon a review of all 8 ARIMA MODELS and then use that common for each state separately to identify the true point of the level shift for that state. Now with a common model and an Intervention Series reflecting a composite of the 8 Intervention SEries locall identified , estimate a Global set of coefficients for the ARIMA MODEL and the ONE INTERVENTION SERIES. This might get dicey where you might need to cleanse each of the eight series by adjusting for Pulse Outliers. $\endgroup$ – IrishStat Nov 21 '11 at 22:59

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.