Small sample properties of maximum likelihood versus generalized method of moments based tests for spatially autocorrelated errors

Peter Egger; Mario Larch; Michael Pfaffermayr; Janette Walde

This paper undertakes a Monte Carlo study to compare MLE-based and GMM-based tests regarding the spatial autocorrelation coefficient of the error term in a Cliff and Ord type model. The main finding is that a Wald-test based on GMM estimation as derived by Kelejian and Prucha (2005a) performs surprisingly well. Our Monte Carlo study indicates that the GMM Wald-test is correctly sized even in small samples and exhibits the same power as their MLE-based counterparts. Since GMM estimates are much easier to calculate, the GMM Wald-test is recommended for applied researches.

MoreLess

Year of publication:	Oct. 2005
Authors:	Egger, Peter ; Larch, Mario ; Pfaffermayr, Michael ; Walde, Janette
Publisher:	München : CESifo
Subject:	Statistischer Test \| Statistical test \| Theorie \| Theory \| Maximum-Likelihood-Schätzung \| Maximum likelihood estimation \| Momentenmethode \| Method of moments \| Autokorrelation \| Autocorrelation

freely available

Full text |

More access options

Check Google Scholar

In libraries world-wide (WorldCat)

In German libraries (KVK)

I need help

Extent:	Online-Ressource, 26 S. = 377 KB, Text graph. Darst
Series:	CESifo working papers. - München : [Verlag nicht ermittelbar], ISSN 2364-1428, ZDB-ID 2065232-X. - Vol. 1558
Type of publication:	Book / Working Paper
Type of publication (narrower categories):	Arbeitspapier ; Working Paper ; Graue Literatur ; Non-commercial literature
Language:	English
Notes:	Systemvoraussetzungen: Acrobat reader
Source:	ECONIS - Online Catalogue of the ZBW

Persistent link: https://www.econbiz.de/10003202038