Identification, Estimation and Testing in Panel Data Models with Attrition: The Role of the Missing at Random Assumption
AbstractThis paper discusses identification, estimation and testing in panel data models with attrition. We focus on a situation which often occurs in the analysis of firms: Attrition (exit) is endogenous and depends on the outcomes of an observed stochastic process and the interest-parameters characterizing this process. Thus attrition is non-ignorable even if selection is based only on observed variables - that is, even if the missing items are missing at random (MAR). The likelihood function obtained by ignoring the attrition mechanism is a pseudo likelihood function. Assuming that the MAR condition holds, this paper establishes conditions for identification and consistent estimation based on the pseudo likelihood function. It is also shown that the MAR hypothesis has testable implications in many situations that are encountered in practice. Simulations suggest that in the case of the autoregressive model with random effects, the efficiency of the pseudo likelihood estimator (based on normality) is not much affected even by strong departures from normality. In a variety of simulation models, the pseudo likelihood estimator clearly outperforms the moment estimators - even when the latter are consistent.
Download InfoIf you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
Bibliographic InfoPaper provided by Research Department of Statistics Norway in its series Discussion Papers with number 330.
Date of creation: Sep 2002
Date of revision:
Missing at random; non-ignorable attrition; unbalanced panel data; identification; pseudo likelihood; martingale.;
Find related papers by JEL classification:
- C13 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods and Methodology: General - - - Estimation: General
- C23 - Mathematical and Quantitative Methods - - Single Equation Models; Single Variables - - - Models with Panel Data; Spatio-temporal Models
- C33 - Mathematical and Quantitative Methods - - Multiple or Simultaneous Equation Models; Multiple Variables - - - Models with Panel Data; Spatio-temporal Models
This paper has been announced in the following NEP Reports:
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Hahn, Jinyong, 1999. "How informative is the initial condition in the dynamic panel model with fixed effects?," Journal of Econometrics, Elsevier, vol. 93(2), pages 309-326, December.
- White, Halbert, 1982. "Maximum Likelihood Estimation of Misspecified Models," Econometrica, Econometric Society, vol. 50(1), pages 1-25, January.
- Robert MOFFIT & John FITZGERALD & Peter GOTTSCHALK, 1999. "Sample Attrition in Panel Data: The Role of Selection on Observables," Annales d'Economie et de Statistique, ENSAE, issue 55-56, pages 129-152.
- Joel L. Horowitz & Charles F. Manski, 1996.
"Censoring of Outcomes and Regressors Due To Survey Nonresponse: Identification and Estimation Using Weights and Imputations,"
9602007, EconWPA, revised 06 Mar 1996.
- Horowitz, Joel L. & Manski, Charles F., 1998. "Censoring of outcomes and regressors due to survey nonresponse: Identification and estimation using weights and imputations," Journal of Econometrics, Elsevier, vol. 84(1), pages 37-58, May.
- Horowitz, J.L. & Manski, C.F., 1995. "Censoring of Outcomes and Regressors Due to Survey Nonresponse: Identification and estimation Using Weights and Imputations," Working Papers 95-12, University of Iowa, Department of Economics.
- Heckman, James, 2013.
"Sample selection bias as a specification error,"
Publishing House "SINERGIA PRESS", vol. 31(3), pages 129-137.
- Gourieroux, Christian & Monfort, Alain & Trognon, Alain, 1984.
"Pseudo Maximum Likelihood Methods: Theory,"
Econometric Society, vol. 52(3), pages 681-700, May.
- Blundell, Richard & Bond, Stephen, 1998.
"Initial conditions and moment restrictions in dynamic panel data models,"
Journal of Econometrics,
Elsevier, vol. 87(1), pages 115-143, August.
- Blundell, R. & Bond, S., 1995. "Initial Conditions and Moment Restrictions in Dynamic Panel Data Models," Economics Papers 104, Economics Group, Nuffield College, University of Oxford.
- R Blundell & Steven Bond, . "Initial conditions and moment restrictions in dynamic panel data model," Economics Papers W14&104., Economics Group, Nuffield College, University of Oxford.
- Richard Blundell & Steve Bond, 1995. "Initial conditions and moment restrictions in dynamic panel data models," IFS Working Papers W95/17, Institute for Fiscal Studies.
- Hausman, Jerry A & Wise, David A, 1979. "Attrition Bias in Experimental and Panel Data: The Gary Income Maintenance Experiment," Econometrica, Econometric Society, vol. 47(2), pages 455-73, March.
- J, A, Abowd & Bruno Crépon & Francis Kramarz, 1997.
"Moment Estimation with Attrition,"
97-35, Centre de Recherche en Economie et Statistique.
- Arellano, Manuel & Bover, Olympia, 1995.
"Another look at the instrumental variable estimation of error-components models,"
Journal of Econometrics,
Elsevier, vol. 68(1), pages 29-51, July.
- M Arellano & O Bover, 1990. "Another Look at the Instrumental Variable Estimation of Error-Components Models," CEP Discussion Papers dp0007, Centre for Economic Performance, LSE.
- Ahn, Seung C. & Schmidt, Peter, 1995. "Efficient estimation of models for dynamic panel data," Journal of Econometrics, Elsevier, vol. 68(1), pages 5-27, July.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (J Bruusgaard).
If references are entirely missing, you can add them using this form.