Linear regression using both temporally aggregated and temporally disaggregated data: Revisited

Qian, Hang (2010): Linear regression using both temporally aggregated and temporally disaggregated data: Revisited.

Abstract

This paper discusses regression models with aggregated covariate data. Reparameterized likelihood function is found to be separable when one endogenous variable corresponds to one instrument. In that case, the full-information maximum likelihood estimator has an analytic form, and thus outperforms the conventional imputed value two-step estimator in terms of both efficiency and computability. We also propose a competing Bayesian approach implemented by the Gibbs sampler, which is advantageous in more flexible settings where the likelihood does not have the separability property.

• Item Type: MPRA Paper
• Language: English
• Keywords: Aggregated covariate; Maximum likelihood; Bayesian inference
• Subjects: C - Mathematical and Quantitative Methods > C1 - Econometric and Statistical Methods and Methodology: General > C13 - Estimation: General; C - Mathematical and Quantitative Methods > C1 - Econometric and Statistical Methods and Methodology: General > C11 - Bayesian Analysis: General

References

Allison, P. D., 2000. Multiple imputation for missing data: a cautionary tale. Sociological methods and Research 28, 301-309.

Anderson, T. W., 1957. Maximum likelihood estimates for a multivariate normal distribution when some observations are missing. Journal of the American Statistical Association 52 (278), 200-203.

Andreou, E., Ghysels, E., Kourtellos, A., 2010. Regression models with mixed sampling frequencies. Journal of Econometrics.

Bureau of Labor Statistics, U.S. Department of Labor, 2010. Occupational Outlook Handbook. Washington: U.S. Government Printing Office.

Dagenais, M. G., 1973. The use of incomplete observations in multiple regression analysis: A generalized least squares approach. Journal of Econometrics 1 (4), 317-328.

Fraser, D. A. S., 1951. Normal samples with linear constraints and given variances. Canadian Journal of Mathematics 3, 363-366.

Geweke, J. F., 1978. Temporal aggregation in the multiple regression model. Econometrica 46 (3), 643-61.

Geweke, J. F., 1995. Bayesian inference for linear models subject to linear inequality constraints. Working Papers 552, Federal Reserve Bank of Minneapolis.

Ghysels, E., Santa-Clara, P., Valkanov, R., 2006. Predicting volatility: getting the most out of return data sampled at di_erent frequencies. Journal of Econometrics 131 (1-2), 59-95.

Gourieroux, C., Monfort, A., 1981. On the problem of missing data in linear models. Review of Economic Studies 48 (4), 579-86.

Hsiao, C., 1979. Linear regression using both temporally aggregated and temporally disaggregated data. Journal of Econometrics 10 (2), 243-252.

Koop, G., Poirier, D. J., Tobias, J. L., 2007. Bayesian Econometric Methods. Cambridge Books. Cambridge University Press.

Palm, F. C., Nijman, T. E., 1982. Linear regression using both temporally aggregated and temporally disaggregated data. Journal of Econometrics 19 (2-3), 333-343.

Rubin, D. B., 1987. Multiple imputation for nonresponse in surveys. New York: Wiley.

Schafer, J. L., 1997. Analysis of incomplete multivariate data. London: Chapman and Hall.

Van Buuren, S., Boshuizen, H. C., Knook, D. L., 1999. Multiple imputation of missing blood pressure covariates in survival analysis. Statistics in Medicine 18, 681-694.