I have multiple quarterly time series data and trying to build a linear regression model using this dataset.

  1. Should the transformations on the LHS and RHS be the same i.e QoQ percent changes?

  2. Could we have Qi/Qi-4 percentage changes on the independent variables to predict QoQ (Qi/Qi-1) changes in response variable?

  3. If yes, is there any literature or book that illustrates or refutes this fact.

  • 1
    $\begingroup$ Why "linear regression" for time-series? Did you consider ARIMA? $\endgroup$ – Sergey Bushmanov Oct 15 '15 at 22:33
  • $\begingroup$ Try reading this St. Louis FED publication $\endgroup$ – london Oct 16 '15 at 12:05
  • $\begingroup$ Yes. I have tried ARIMAX (1,0,0), gives you similar results as OLS. I have read this pub., it talks about modeling lhs and RHS which are at different frequencies and coverting to one or the other , in my case the frequency of the dataset is the same quarterly. I am trying to find out if quarterly changes can be explained by yearly changes and whether the necessary residuals test will hold. $\endgroup$ – HDX Oct 17 '15 at 0:17

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.