Hello to everyone on the forum,

I am currently working with intraday electricity price data. In the electricity market each hour is considered as a different product, because the demand and production mix for each hour is different. Because of the above, for my econometric analysis, I consider my data as panel data where each hour is a different individual and where (from the various tests) I conclude that I must apply fixed effects. However, the times I have presented my project, the audience finds it strange and difficult to understand why I use panel data and not time series. After some thought, I came to a possible answer: my time series would be like having a pooled OLS and, therefore, I have already considered it, and after doing a wald test, I have discarded it. Is my answer correct, or how would you justify it.

Thank you very much for your help!

  • $\begingroup$ I am not sure before seeing your model, but why don't you just say that you include hour dummies (or hour fixed effects) without referring to panel data? $\endgroup$
    – chan1142
    Feb 27 at 3:12

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.