Mixed signals among tests for cointegration (replication data)

DOI

This paper illustrates that, under the null hypothesis of no cointegration, the correlation of p-values from a single-equation residual-based test (i.e., ADF or ) with a system-based test (trace or maximum eigenvalue) is very low even as the sample size gets large. With data-generating processes under the null or near it, the two types of tests can yield virtually any combination of p-values regardless of sample size. As a practical matter, we also conduct tests for cointegration on 132 data sets from 34 studies appearing in this Journal and find substantial differences in p-values for the same data set.

Identifier
DOI https://doi.org/10.15456/jae.2022314.1316340166
Metadata Access https://www.da-ra.de/oaip/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:oai.da-ra.de:776198
Provenance
Creator Gregory, Allan W.; Haug, Alfred A.; Lomuto, Nicoletta
Publisher ZBW - Leibniz Informationszentrum Wirtschaft
Publication Year 2004
Rights Creative Commons Attribution 4.0 (CC-BY); Download
OpenAccess true
Contact ZBW - Leibniz Informationszentrum Wirtschaft
Representation
Language English
Resource Type Collection
Discipline Economics