Hi, I'm working on a multivariate ARIMA model. I have 2 time series and found for each an ARIMA model I'd like to know how are calculated the residuals of my arima model using residuals() function in R ? Is it as I think predicted values (from ARIMA model) - observed values ? Is it relevant to use the residuals of my models to realize the cross-correlation between my 2 time series? Thanks Myriam -- View this message in context: http://www.nabble.com/residuals-in-arima-tp24726955p24726955.html Sent from the R help mailing list archive at Nabble.com.