Tests of Non-Causality Under Markov Assumptions for Qualitative Panel Data
Abstract
For many years, social scientists have been interested in obtaining testable definitions of causality [C. W. Granger (1969)]. Recent works include those of G. Chamberlain (1982) and J. P. Florens and M. Mouchart (1982). The present paper first clarifies the results of these latter papers by considering a unifying definition of non-causality. Then, log-likelihood ratio (LR) tests for non-causality are derived for qualitative panel data under the minimal assumption that one series is Markov. LR tests for the Markov property are also obtained. Both test statistics have closed forms. These tests thus provide a readily applicable procedure for testing non-causality on qualitative panel data. Finally, the tests are applied to French Business Survey data in order to test the hypothesis that price changes from period to period are strictly exogenous to disequilibria appearing within periods.
Additional Information
Revised. Original dated to April 1983. This research was done while the third author was visiting the Universite des Sciences Sociales de Toulouse. Support from DGRST 81-E-1303 is gratefully acknowledged. We are indebted to Jeff Dubin, Dave Grether, Jerry Kramer, Doug Rivers, Howard Rosenthal for helpful criticism, and to Ken McCue for computational assistance. Published as Bouissou, Michel B., Jean-Jacques Laffont, and Quang H. Vuong. "Tests of noncausality under Markov assumptions for qualitative panel data." Econometrica: Journal of the Econometric Society (1986): 395-414.Attached Files
Submitted - sswp501_-_revised.pdf
Files
| Name | Size | Download all |
|---|---|---|
|
md5:e7502ed6c2512c0e4881664244682e78
|
497.3 kB | Preview Download |
Additional details
- Eprint ID
- 81661
- Resolver ID
- CaltechAUTHORS:20170920-164043949
- Direction Générale de la Recherche Scientifique et Technique
- DGRST 81-E-1303
- Created
-
2017-09-21Created from EPrint's datestamp field
- Updated
-
2019-10-03Created from EPrint's last_modified field
- Caltech groups
- Social Science Working Papers
- Series Name
- Social Science Working Paper
- Series Volume or Issue Number
- 501