The author derives the limiting properties of the two-stage least squares estimator of an equation in a dynamic simultaneous model when variables are nonstationary and cointegrated. The implication on hypothesis testing is also discussed. It is shown that, in a structural equation approach, what one needs to worry about are the classical issues of identification and estimation, not nonstationarity and cointegration. Conventional formulae for computing the asymptotic covariance of the two-stage least squares estimator and the Wald-type test statistics remain good approximations despite the fact that variables may be integrated. Copyright 1997 by The Review of Economic Studies Limited.

Identification conditions for binary choice errors-in-variables models are explored. Conditions for the consistency and asymptotic normality of the maximum likelihood estimators of binary choice models with unbounded explanatory variables are given. Two- or three-step estimators to simplify computation are also suggested.

The author demonstrates that despite variables that are integrated, the fundamental issues on structural equation modeling raised by the Cowles Commission remain valid and standard estimation and testing procedures can still be applied. A basic framework linking the multiple time series model and the dynamic simultaneous equation model is provided and implications under the long-run cointegrating relations are discussed. Conditions for identifying both the short-run dynamics and long-run equilibrium conditions are given. Limiting properties of the least squares and simultaneous equation estimators under cointegration are derived. Implications for hypothesis testing are also discussed.

[This paper is concerned with the identification and estimation of the parameters in a dynamic simultaneous equations model with stationary disturbances when both the endogenous and exogenous variables are subject to random measurement errors. A frequency domain approach is suggested to fully utilize the information contained in the data. The first part of this paper explores the identification criteria. The second part of this paper suggests estimation methods for such a model. Both full information and limited information estimation methods are studied and their respective gains and losses are evaluated.]

[The model extlesstex-math extgreater$Y_\it\= extbackslashSigma _\k\( extbackslashbeta _\k\+ extbackslashdelta _\ik\+y_\tk\)x_\ikt\= extbackslashvarepsilon _\it\$ extless/tex-math extgreater with extlesstex-math extgreater$ extbackslashdelta _\ik\$ extless/tex-math extgreater and extlesstex-math extgreatery_\tk\ extless/tex-math extgreater random is considered as a means of pooling the time series of a cross-section sample. The model is placed in a mixed analysis of variance framework. Relationships between various estimation criteria are derived and their asymptotic properties compared. Some implementation problems are also discussed.]