I found auto.arima() function in forecast packages. As far I have understand how it works, It should find the best model for the data, my question is: Is it possible to understand if the variance is not constant during all the period(timeseries) using that function? I mean... If it fit a model it should means that the variance is homoscedastics because i set stationary=TRUE

Let me know, thank you!


1 Answer 1


Returns best ARIMA model according to either AIC, AICc or BIC value. The function conducts a search over possible model within the order constraints provided.

This means it tries all the possible parameters (within the constraints provided) and returns the model with the lowest AIC, AICc or BIC.

For more information, you can read the article referenced in ?auto.arima.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.