Volume 9, Issue 1

This study presents a structural estimation method for nonlinear stochastic dynamic models of heterogeneous firms. I perform a Monte Carlo experiment to evaluate the performance of the estimators for the AR(1) dynamic panel data subject to sample selection without exogenous regressors. The results suggest a strong need to correct the sample selection and that the proposed structural estimation method works well. These results are important for practical situations where the assumptions of the standard sample selection correction methods are not satisfied.

This paper describes a simple and interesting method to introduce and teach undergraduate students about preference estimation using random utility models. The example centers around estimating preferences over rides at Disneyland theme parks and uses actual stated-preference survey data. The lesson is designed to be self-contained in a single 90 minute lecture. Given the strong background that many undergraduate economic students have with consumer choice theory, introducing preference estimation as a real-world application into econometrics curriculum can be an enriching experience.

Most empirical economic research is conducted with the goal of providing scientific evidence that will be informative in assessing causal relationships of interest based on relevant counterfactuals. The implementation of regression methods in this context is ubiquitous. With this as motivation, we detail a comprehensive regression-based potential outcomes framework for causal modeling, estimation and inference. This framework facilitates rigorous specification of the effect parameter of interest and makes clear the sense in which it is causally interpretable, when appropriately defined in a potential outcomes setting. It also serves to crystallize the conditions under which the effect parameter and the underlying regression parameters are identified. The consistent sample analog estimator of the effect parameter is discussed. Juxtaposing this framework with a stylized version of a commonly implemented and routinely applied modeling and estimation protocol reveals how the latter is deficient in recognizing, and fully accounting for, conditions required for identification of the relevant effect parameter and the causal interpretability of estimation results. In the context of an example, we demonstrate the conceptual advantages of this general potential outcomes framework for regression modeling by showing how it resolves fundamental shortcomings in the conventional approach to characterizing and remedying omitted variable bias.

This paper develops an alternative estimator for linear dynamic panel data models based on parameterizing the covariances between covariates and unobserved time-invariant effects. A GMM framework is used to derive an optimal estimator based on moment conditions in levels, with no efficiency loss compared to the classic alternatives like (Arellano, M., and S. Bond. 1991. “Some Tests of Specification for Panel Data: Monte Carlo Evidence and an Application to Employment Equations.” Review of Economic Studies 58 (2): 277–297), (Ahn, S. C., and P. Schmidt. 1995. “Efficient Estimation of Models for Dynamic Panel Data.” Journal of Econometrics 68 (1): 5–27) and (Ahn, S. C., and P. Schmidt. 1997. “Efficient Estimation of Dynamic Panel Data Models: Alternative Assumptions and Simplified Estimation.” Journal of Econometrics 76: 309–321). Still, we show analytically and by Monte Carlo simulations that the new procedure leads to efficiency improvements for certain data generating processes. The framework also leads to a very simple test for unobserved effects.

Structural asymmetric first-price auction estimation methods have provided numerous empirical studies. However, due to the latent nature of underlying valuations, the accuracy of estimates is not feasibly testable with field data, a fact that could inhibit empirical auction market designs and applications based on structural estimates. To assess their accuracy, we provide an analysis of estimates derived from experimental asymmetric auction data, in which researchers observe valuations. We test the null of statistical equivalence between the estimated and true value distributions against the alternative of non-equivalence. When advanced models are used, the Modified Kolmogorov-Smirnov test fails to reject the distributional equivalence, supporting structural asymmetric auction estimations for auction market studies. In addition, recovered efficiencies have plus-minus 2.5 percent precision, compared to the true efficiencies.

Rao’s (1948) seminal paper introduced a fundamental principle of testing based on the score function and the score test has local optimal properties. When the assumed model is misspecified, it is well known that Rao’s score (RS) test loses its optimality. A model could be misspecified in a variety of ways. In this paper, we consider two kinds: distributional and parametric. In the former case, the assumed probability density function differs from the data generating process. Kent (1982) and White (1982) analyzed this case and suggested a modified version of the RS test that involves adjustment of the variance. In the latter case, the dimension of the parameter space of the assumed model does not match with that of the true one. Using the distribution of the RS test under this situation, Bera and Yoon (1993) developed a modified RS test that is valid under the local parametric misspecification. This involves adjusting both the mean and variance of the standard RS test. This paper considers the joint presence of the distributional and parametric misspecifications and develops a modified RS test that is valid under both types of misspecification. Earlier modified tests under either type of misspecification can be obtained as the special cases of the proposed test. We provide three examples to illustrate the usefulness of the suggested test procedure. In a Monte Carlo study, we demonstrate that the modified test statistics have good finite sample properties.

This paper compares the “forecasting approach” and the “fully interacted approach” to estimation of cartel damages. We investigate the impact of relaxing the assumptions of exogeneity and stationarity, both theoretically and in Monte Carlo simulations. The results suggest that the advantages of the fully interacted approach are less clear and that the forecasting approach may be more robust to the relaxations of some of these maintained assumptions.

The paper proposes new instrumental variables estimators for the slope parameters of a panel data model with classical endogeneity in which all the observables – including the instruments – may have a common factors structure. These estimators are shown to be consistent and asymptotically normal under weak regularity conditions. A small Monte Carlo simulation shows that these estimators compare favourably to existing estimators.