In a multiple regression, is it correct to regress seasonal data with non seasonal data? If it is not, how can I adjust the series in order to make forecasts?
Asked
Active
Viewed 214 times
0
-
Could you explain what you mean by "seasonal data"? Are the explanatory variables or responses seasonal? What are the variables, specifically, and do they include time among the explanatory variables? – whuber May 31 '19 at 13:08
-
I forgot to mention. Both are time series data and they are used as explanatory variables. – Richardi Ferreira Silva Jun 01 '19 at 21:53
1 Answers
0
Yes, you can mix data types. In general you might want to look at this discussion material about regression with time series data. http://autobox.com/dave/regvsbox.pdf (which I authored) discusses issues/differences/opportunities/pitfalls when dealing with time series that your possible regression solutions may be ignoring.
Also The theory behind fitting an ARIMAX model and Transfer Function Clarification might be of interest to you.
IrishStat
- 27,906
- 5
- 29
- 55
-
-
Thank you for your nice words .If you want to close the question you can accept my answer and/or upvote it. If I can help explain more I would be glad to help, perhaps in a chat room. – IrishStat Jun 02 '19 at 02:19