Using Suest to test coefficients across ARIMA models

[Josh Ingber]

Hello,
I am running several ARIMA models and I want to test the equivalence of the coefficients with the test command. However, I get the following error:
first was estimated with a nonstandard vce (opg) where "first" is the name of my first model. To be clear, here is the code I am running.


quietly arima lmp d1.lp if fp==1, arima(1,0,2)
estimates store first

quietly arima lmp d1.lp if sp==1, arima(2,0,0)
estimates store second

quietly arima lmp d1.lp if tp==1, arima(1,0,0)
estimates store third

quietly arima lmp d1.lp, arima(1,0,2)
estimates store whole

suest first second third whole

Thanks....Any substitutes if it doesn't work?
Joshua

[Phil Bromiley]

You didn't get a quick answer. You'll improve your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex. Being able to replicate your problem would help a lot in diagnosing it. Also, you can simplify what you present to the minimum needed to demonstrate the difficulty.

I don't use arima, but using the data from the documentation, I get the same problem. Changing the arima() options didn't fix it. I suspect the issue is that suest does not accept certain forms of errors in the basic models, and arima may automatically include such errors. suest likes simple error structures and arima is about a more complex error structure. If this were regression, I'd say use dummy variables to estimate all the models in one run, but I suspect this doesn't work in regression. I wonder if there are some other estimators that might give you the same model as arima.

Sorry I can't be of more assistance.

[Josh Ingber]

Phil, Thank you for thinking about it...I didn't read the FAQ, I will! I'll keep trying to solve the problem, which I never really stated! Let me take the opportunity to say what I am trying to do more specifically in case some one knows of an alternative. I have three different ARIMA models... They vary but they share a variable in common, and are from different periods. I want to do an F-test or Chou Test to see if they are statistically the same or different over the course of the differing periods/circumstances.