Peter Lundquist: Dept. of Economic Statistics, Stockholm School of Economics
Abstract: Analysts using data from official statistical authorities often neglect the fact that data frequently are collected using sample surveys. In this paper the impact of sampling error on the estimation of the autocovariance and the autocorrelation function is studied under a micro based superpopulation time series model. Uncritical use of data published by statistical agencies may result in biased estimators. The bias is caused by the sampling error and is different from aggregation bias. Different estimators are investigated theoretically as well as with the help of simulations.
79 pages, November 1994
Questions (including download problems) about the papers in this series should be directed to Helena Lundin ()
Report other problems with accessing this service to Sune Karlsson ().
This page generated on 2018-03-27 10:24:37.