you could then make that data wide by having a column for each countries' monthly time series. If you are strictly speaking about a data storage, yes those are two ways to arrange the same data. If you agree they are equivalent then we agree. ![]() It does not matter that they are stored differently.įrom a data modeling perspective a time-series model compared to a panel model is vastly different. You are letting 'time series model' carry a lot of weight here for you. #How to compare multiple cross sections over time hypack series# Yes, if you try to run an ARIMA on a panel of data, that is just going to go badly. It's a univariate technique.įrom the perspective of someone who develops packages for "data modeling", I advise you to go check out how most packages handle panel data. #How to compare multiple cross sections over time hypack series#.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |