{ "cells": [ { "attachments": {}, "cell_type": "markdown", "id": "2e3d942c", "metadata": {}, "source": [ "# Reducing autocorrelation\n", "*R.A. Collenteur, University of Graz*\n", "\n", "In this notebook we look at two strategies that may help to reduce the autocorrelation in the noise, such that the estimated standard errors of the parameters may be used for further analysis. \n", "\n", "- The first strategy is to change the time interval between the groundwater level observations by removing observations. \n", "- The second strategy is the use of the ARMA(1,1) noise model instead of the default AR(1) noise model. \n", "\n", "To show the effects of these strategies we look at example models for a groundwater level time series observed near the town of Wagna in Southeastern Austria. This analysis is based on the study from [Collenteur et al. (2021)](#References). \n", "\n", "