The Department of Economics will be sponsoring a session at the 33rd New England Statistics Symposium (NESS) on May 15–17, 2019.
High Dimensional Econometrics
The technological innovations in information processing and the increased storage capability have made possible to collect very large data sets in various fields of economics and finance.
This session puts together 3 papers that present state-of-the-art techniques to deal with high dimensional issues in econometrics.
List of invited speakers:
(1) Fa Wang, Cass Business School, Fa.Wang@city.ac.uk, “Maximum Likelihood Estimation and Inference for High Dimensional Nonlinear Factor Models with Application to Factor-augmented Regressions”
(2) Yuan Liao, Rutgers Economics, firstname.lastname@example.org, “Inference for Heterogeneous Effects Using Low Rank Estimation”
(3) Min Seong Kim, UConn Economics, email@example.com, “Policy Analysis Using Panel and Multilevel Models with Group Interactive Fixed Effects”
Discussant: Jungbin Hwang, UConn Economics, firstname.lastname@example.org
Session Chair: Chihwa Kao, UConn Economics, email@example.com
Information about the conference may be found online at https://symposium.nestat.org/
Professor Jungbin Hwang’s paper “Should We Go One Step Further? An Accurate Comparison of One-step and Two-step Procedures in a Generalized Method of Moments Framework”, co-authored with Yixiao Sun, has been accepted for publication in the Journal of Econometrics, one of the top scholarly journals in theoretical econometrics. The paper started as a third-year paper project when Professor Hwang was a graduate student in the University of California, San Diego.
Professor Hwang’s paper provides an assessment of the merits of the first step GMM estimator and test relative to the two-step GMM estimator and test. The article shows the two-step procedure outperforms the one-step method only when the benefit of using the optimal weighting matrix outweighs the cost of estimating it. The qualitative message applies to both the asymptotic variance comparison and power comparison of the associated tests.
According to the conventional asymptotic theory, the two-step Generalized Method of Moments (GMM) estimator and test perform as least as well as the one-step estimator and test in large samples. The conventional asymptotic theory, as elegant and convenient as it is, completely ignores the estimation uncertainty in the weighting matrix, and as a result it may not reflect finite sample situations well. In this paper, we employ the fixed-smoothing asymptotic theory that accounts for the estimation uncertainty, and compare the performance of the one-step and two-step procedures in this more accurate asymptotic framework. We show that the two-step procedure outperforms the one-step procedure only when the benefit of using the optimal weighting matrix outweighs the cost of estimating it. This qualitative message applies to both the asymptotic variance comparison and power comparison of the associated tests. A Monte Carlo study lends support to our asymptotic results.
Professor Jungbin Hwang and his co-author Yixiao Sun have had their paper, “Simple, Robust, and Accurate F and t Tests in Cointegrated Systems,” accepted by Econometric Theory as a lead article in a future issue.
In this paper, they propose new, simple, and more accurate statistical tests in a cointegrated system that allows for endogenous regressors and serially dependent errors. The approach involves first transforming the time series using orthonormal basis functions in L-2 space, which have energy concentrated at low frequencies, and then running an augmented regression based on the transformed data and constructing the test statistics in the usual way. The F and t tests developed in this article, are extremely simple to implement have more accurate size in finite samples than existing tests such as the asymptotic chi-squared and normal tests based on the fully modified OLS estimator of Phillips and Hansen (1990) and can be made as powerful as the latter test.
Professor Jungbin Hwang has published the paper “Asymptotic F and t tests in an efficient GMM setting” with his co-author Yixiao Sun in the Journal of Econometrics Volume 198, Issue 2, June 2017, Pages 277-295.
In this paper, they propose a simple and easy-to-implement modification to the trinity of test statistics in the two-step efficient GMM setting and show that the modified test statistics are all asymptotically F distributed under the so-called fixed-smoothing asymptotics. The main contributions of this paper are developing convenient asymptotic F tests whose critical values, i.e., the standard F critical values, are readily available from standard statistical tables and programming environments. For testing a single restriction with a one-sided alternative, the paper also develops an asymptotic test theory using the standard t distribution as the reference distribution.
The Economics Department is happy to welcome four faculty who joined UConn at the beginning of the Fall Semester. Chihwa (Duke) Kao, formerly at Syracuse University, joined the economics department as its new Department Head. Kao is a renowned econometrician working on time series and panel data topics.
Jungbin Hwang also joined the faculty as an Assistant Professor this Fall after completing his Ph.D. at the University of California San Diego. Hwang is also an econometrician working on panel data and time series topics.
Hyun Lee also joins the faculty as an Assistant Professor after completing his Ph.D. at the University of Chicago. Hyun is a macroeconomist who works on topics related to economic growth and policy analysis.
Patricia Ritter joins the faculty as an Assistant Professor following completion of her Ph.D. at the University of Chicago. Dr. Ritter works on topics at the intersection of development and health.