Hi list, I am trying to fit arima model for a grid of 360x161x338 points, where 360x161 is the spatial dimension and 338 is the number of time steps I have, which is seasonal. For this purpose I used the auto.arima function in forecast package. After fitting residuals at each grid in space, the auto correlations are still significant ( but < 0.2). This make me think that the data could be spatially correlated as well. In such case is it necesary to remove spatial autocorelations before fitting models in time and are there some methods available in R to remove the spatial autocorrelations. Thanks nuncio
-- Nuncio.M Research Scientist National Center for Antarctic and Ocean research Head land Sada Vasco da Gamma Goa-403804 [[alternative HTML version deleted]] ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.