Hey guys,
I have a question. I've a time series sampled every minute. The fact is that I need to forecast the next 1/2/3 hours and so it will be impossible to deal with this data too frequent. I was thinking of doing a sample of 20/30 min and take a representative value associated to it to create a new time series.
My first idea is to take the mean or the median.
Is it a good idea? Other ideas?
Referred here by Forecasting: Principles and Practice, by Rob J Hyndman and George Athanasopoulos