Consistent Covariance Matrix Estimation in Probit Models with Autocorrelated Errors
Authors:
- Arturo EstrellaAEArturo Estrella
Preprint
- 1 April 1998
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Some recent time-series applications use probit models to measure the forecasting power of a set of variables. Correct inferences about the significance of the variables requires a consistent estimator of the covariance matrix of the estimated model coefficients. A potential source of inconsistency in maximum likelihood standard errors is serial correlation in the underlying disturbances, which may arise, for example, from overlapping forecasts. We discuss several practical methods for constructing probit autocorrelation-consistent standard errors, drawing on the generalized method of moments techniques of Hansen (1982), Newey-West (1987) and others, and we provide simulation evidence that these methods can work well.Keywords
This publication has 15 references indexed in Scilit:
- Predicting U.S. Recessions: Financial Variables as Leading IndicatorsReview of Economics and Statistics, 1998
- The Term Structure as a Predictor of Real Economic ActivityThe Journal of Finance, 1991
- Heteroskedasticity and Autocorrelation Consistent Covariance Matrix EstimationEconometrica, 1991
- Efficient instrumental variables estimation of systems of implicit heterogeneous nonlinear dynamic equations with nonspherical errors1988
- jacques poucet. Les origines de Rome: Tradition et histoire. (Publications des Facultés Universitaires Saint-Louis, number 38.) Brussels: Facultés Universitaires Saint-Louis. 1985. Pp. 360The American Historical Review, 1988
- Nonlinear Statistical Models1987
- Bank Rate Policy Under the Interwar Gold Standard: A Dynamic Probit ModelThe Economic Journal, 1985
- Multiperiod Probit Models and Orthogonality Condition EstimationInternational Economic Review, 1983
- Time series: Data analysis and theory. Expanded Edition. By David R. Brillinger. Holden-Day, Inc., San Francisco, 1981. xii + 540 pp. U.S. $28.95. ISBN 0-8162-1150-7Canadian Journal of Statistics, 1982
- The Maximum Likelihood, the Minimum Chi-Square and the Nonlinear Weighted Least-Squares Estimator in the General Qualitative Response ModelJournal of the American Statistical Association, 1976