Journal Article
No. 2012-20 |
June 06, 2012
Abstract
The authors address the issue of estimation and inference in dependent non-stationary panels of small cross-section dimensions. The main conclusion is that the best results are obtained applying bootstrap inference to single-equation estimators, such as fully modified ordinary least squares and dynamic ordinary least squares. Seemingly unrelated regression estimators perform badly, or are even unfeasible, when the time dimension is not very large compared to the cross-section dimension.
JEL Classification
C15
C23
C33
Citation
Francesca Di Iorio and Stefano Fachin
(2012).
A Note on the Estimation of Long-Run Relationships in Panel Equations with Cross-Section Linkages.
Economics: The Open-Access, Open-Assessment E-Journal,
Vol. 6,
2012-20.
http://dx.doi.org/10.5018/economics-ejournal.ja.2012-20

Google+
Twitter
Facebook





The use of the word "panels" as well as that of "structure" implies (to this engineer) that the paper is about the strength or elasticity of a space-frame! There is no explanation of what kind of panel is being considered not any direct reference to another paper where this term ...[more]
... is introduced and explained. Further, there are no diagrams in the paper which might help the reader to see what is being considered in more practical terms. In other words, this paper is so specialized that it has no place in this form in a journal that is intended to cover the more general subject of economics.
We are sorry to have unvoluntarily confused the reader. However, we plead innocent, as at the very outset of the paper the meaning of the term “panel” is clearly explained: “N units, observed over T time periods”. In fact, this is pretty close to first meaning provided by the Merriam-Webster ...[more]
... online dictionary (“a list or group of persons selected for some service”), with the engineering meaning (“a separate or distinct part of a surface”) ranking second.
We do not provide references for background reading, such as textbooks, because this is not commonly done in scientific papers. However, an easily accessible source is Wikipedia: the entry "panel data" is a concise but complete introduction to the field.