My research is mostly about GMM and generalized empirical likelihood. Publications Efficient Bootstrap with Weakly Dependent Processes (.pdf and WP .pdf, with F. Bravo, forthcoming Computational Statistics and Data Analysis) Abstract: This paper develops Brown and Newey (2002) efficient bootstrap methodology for moment condition models with weakly dependent observations. The resulting bootstrap procedure is shown to be asymptotically valid and its finite sample performance is assessed using simulations. Working papers Abstract: This paper gives a new jackknife estimator for instrumental variable inference with unknown heteroskedasticity. The estimator is derived by using a method of moments approach similar to the one that produces LIML in case of homoskedasticity. The estimator is symmetric in the endogenous variables including the dependent variable.
Many instruments and many weak instruments asymptotic distributions are derived using high-level assumptions that allow for the simultaneous presence of weak and strong instruments for different explanatory variables. Standard errors are formulated compactly. We review briefly known estimators and show in particular that the symmetric jackknife estimator performs well when compared to the HLIM and HFUL estimators of Hausman et al. (2011) in Monte Carlo experiments. On the Finite Sample Properties of Conditional Empirical Likelihood Estimators (2011, .pdf, with Z. Sándor, submitted) Abstract: We provide Monte Carlo evidence on the finite sample behavior of the conditional empirical likelihood (CEL) estimator of Kitamura, Tripathi, and Ahn (2004) and the conditional Euclidean empirical likelihood (CEEL) estimator of Antoine, Bonnal, and Renault (2007) in the context of a heteroskedastic linear model with an endogenous regressor. We compare these estimators with three heteroskedasticity-consistent instrument-based estimators in terms of various performance measures. Our results suggest that the CEL and CEEL with fixed bandwidths may suffer from the no-moment problem, similarly to the unconditional generalized empirical likelihood estimators studied by Guggenberger (2008). We also study the CEL and CEEL estimators with automatic bandwidths selected through cross-validation. We do not find evidence that these suffer from the no-moment problem. When the instruments are weak, we find CEL and CEEL to have finite sample properties --in terms of mean squared error and coverage probability of confidence intervals-- poorer than the heteroskedasticity-consistent Fuller (HFUL) estimator. In the strong instruments case the CEL and CEEL estimators with automatic bandwidths tend to outperform HFUL in terms of mean squared error, while the reverse holds in terms of the coverage probability, although the differences in numerical performance are rather small. Z-Estimators and Auxiliary Information under Weak Dependence (2010, .pdf) Abstract: In this paper we introduce a weighted Z-estimator for moment condition models in the presence of auxiliary information on the unknown distribution of the data under the assumption of weak dependence. The resulting weighted estimator is shown to be consistent and asymptotically normal. Its small sample properties are checked via Monte Carlo experiments. GMM, Generalized Empirical Likelihood, and Time Series (2009, .pdf) Abstract: In what follows we generalize the results of Kitamura (1997) for BEL to the more general class of Blockwise (B)GEL estimators. The resulting BGEL estimator is proven to be consistent and asymptotically normal and attains the semiparametric lower bound. In addition, we define the BGEL version of the classical trinity of tests, Wald, Lagrange Multiplier, and Likelihood Ratio tests. We find via Monte Carlo experiments that the overidentification tests that stem from the BGEL estimator have generally better small sample properties than the J-test. Work in progress Block Bootstrap with Auxiliary Information (2011, with V. Petrikaite, in progress) |