AbstractWe sketch the proof of some theorems that show how to estimate the parameters in linear regressions, finite moving averages, and in finite order, stationary auto regressions. Some of these estimates have not been studied yet, but the chief novelty is that existing theory is extended to include processes with infinite variance. A main result is that ordinary least squares estimates are consistent for both finite moving average processes and finite order auto regressions. The sampling properties of some of these estimates are indicated.
SubjectsStable Process, Autoregressive Process, Moving Average Process, Regression
RightsThis Item is protected by copyright and/or related rights.You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use.For other uses you need to obtain permission from the rights-holder(s).