Discussion Paper

No. 2012-26 | May 24, 2012
Consistent Estimation of Pseudo Panels in the Presence of Selection Bias

Abstract

In the presence of selection bias, traditional estimators of pseudo panel data are inconsistent. In this paper, the authors derive the conditions under which consistence is achieved in pseudo-panel estimation and propose a simple test of selection bias. Specifically, they propose a Wald test for the null hypothesis that there is no selection bias. Under rejection of the null hypothesis, the authors can consistently estimate pseudo-panel parameters. They use cross sections and pseudo-panel regressions to test for selection bias and estimate the returns to education in Colombia. The authors corroborate the existence of selection bias and find that returns to education are around twenty percent.

Data Set

Data sets for articles published in "Economics" are available at Dataverse. Please have a look at our repository.

The data set for this article can be found at: http://hdl.handle.net/1902.1/18310

JEL Classification

C23 C52

Cite As

Jhon James Mora Rodriguez and Juan Muro (2012). Consistent Estimation of Pseudo Panels in the Presence of Selection Bias. Economics Discussion Papers, No 2012-26, Kiel Institute for the World Economy. http://www.economics-ejournal.org/economics/discussionpapers/2012-26

Assessment



Comments and Questions


Sunil Sapra - Comments to the authors
June 20, 2012 - 00:01

I would like to offer the following comments to the authors.

1. The paper does not discuss the size and the power properties of the proposed test for sample selection bias in pseudo panels; it merely presents an application of the test.

2. It is not clear why ...[more]

... the authors chose to use the Wald test over the Likelihood Ratio test and the Score test given that the Wald test is not invariant to monotonic transformations of the restrictions and has other well-known disadvantages.

3. Wald test uses the approximation that the standard errors of estimates are known. Unlike the likelihood ratio test, it requires a reasonably accurate estimate of the covariance matrix of the parameter estimates.

4. Minor: The word "consistency" is misspelled as "consistence". The assumptions and their motivations are not clearly presented. Why do you need to include proofs in assumptions? Correcting some grammatical errors would certainly help.


José M. Arranz - Comments to the authors
June 26, 2012 - 14:29

This paper contains new and significant information adequate to apply a simple testing procedure for sample selection bias in pseudo panels. I think that if justify its publication in the journal.

I would like to know if the test proposed by the authors is affected by the size ...[more]

... of N(observations) and T(waves).

I Agree with the comments of Sunil Sapra about why the authors use Wald test over LR and Score test. I will appreciate more discussion about it.

In page 3, line 30: where is vi(t),t?


Anonymous - Referee Report
November 14, 2012 - 08:33

see attached file