Regardless of this, the diagnostics tests that may be performed remain the same. Practice in Pastas models, these can come from ml.noise() or ml.residuals(). We will refer to the series that was minimized during parameter estimation as the “residuals”. Diagnostics checks are performed on the residual or noise series of a model, depending on whether or not a noisemodel was applied in the modeling process. Readers who want to get a quick overview of how to perform diagnostic checks on Pastas models are referred to section 2, while sections 3 to 6 are recommended for readers looking for in-depth discussions of the individual methods.ĭiagnostic Checking in Pastas in Practiceĭiagnostic checking is a common step in the time series modeling process, subjecting a calibrated model to various statistical tests to ensure that the model adequately describes the observed time series (Hipel & McLeod, 2005). This notebook provides an overview of the different methods that are available for diagnostic checking of the models residuals in Pastas. Collenteur, University of Graz, July 2020.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |