headshot photo

Xin Liu


Assistant Professor, Economics

Washington State University

xin.liu1@wsu.edu

Office: Hulbert Hall

Google Scholar profile

Curriculum Vitae


Fields of Interests:

Econometric Theory, Applied Econometrics, Quantile Regression, Panel Data


Working Papers

Finite-Sample Auction Inference Using Transaction Prices

2024, submitted
(with David M. Kaplan)

paper | code/tex/etc.

We provide finite-sample, nonparametric, uniform confidence bands for the underlying bid quantile function under symmetric IPV when only the transaction price is observed (i.e., only one order statistic). It extends to finite-sample CIs for various counterfactuals and economic quantities of interest. We make two extensions: a) varying number of bidders, b) auction-level unobserved heterogeneity (including new bounds). Empirically, we examine the heterogeneity across number of bidders (wrt "exogenous participation") and observed auction characteristics.

Quantile Regression with Log(0) Outcomes

2025, submitted
(with David M. Kaplan)

paper | code/tex/etc.

We consider quantile regression when the outcome is the log of a non-negative variable that can equal zero. Unlike the analogous mean regression, this is well-defined if the quantile level is not low enough to include the extensive margin, but "log-like" transformations are used in practice due to computational obstacles. We provide computational solutions and diagnostics, as well as theoretical results including identification, coefficient interpretation under proper specification, characterization of the misspecified log-linear model's estimand, and sensitivity of this estimand to changes in the conditional distribution. To illustrate these results, we revisit an empirical study of armed-group and civilian violence.

Multiple Testing for Distributional Differences with Non-iid Data

2025, submitted
(with David M. Kaplan)

paper | tex/etc.

We propose multiple testing procedures and confidence sets to compare distributions that allow for non-iid data. The MTP have the coherence and consonance property. The confidence sets provide richer information than a global test. Computation is simple and fast.

A Quantile-based Nonadditive Fixed Effects Model

2025, submitted

paper | code/tex/etc.

I propose a structural panel model to study quantile-based heterogeneous causal effects, while allowing endogeneity. This model connects to both the standard fixed effects model and certain fixed effects quantile regression model (Canay 2011) to have quantile-related interpretations.

Inference for Panel Quantile Regression with Time-Invariant Rank

2022, submitted

paper | code

I construct uniform confidence bands and bootstrap confidence interval for a quantile-based heterogeneous causal effects function in a nonadditive fixed effects model.

Dairy Trade Policy and Friction Analyses: (New) Gravity Estimations

2025, submitted
(with Magda Kondaridze and Jeff Luckstead)

We study the counterfactual distributional effect of dairy trade policy and friction variables using a recent distribution regression method (Chernozhukov, Fernández-Val, and Weidner, 2024). We revisit the mean effect using a recent PPML method (Weidner and Zylkin, 2021), which rigorously corrects the bias from incidental parameter problem.  


Publications

Averaging Estimation for Instrumental Variables Quantile Regression

2024, Oxford Bulletin of Economics and Statistics

published | accepted | code | online appendix

I propose averaging methods to improve IVQR estimation efficiency.

Testing in smoothed GMM quantile models with an application to quantile Euler equation

Forthcoming, Econometrics and Statistics

published | accepted | code

I propose testing methods in smoothed GMM quantile model (de Castro, Galvao, Kaplan, and Liu, 2019), with quantile Euler equation empirical example. As a separate contribution, I also provide the large sample theory for the constrained smoothed GMM estimator in the quantile model.

Confidence Intervals for Intentionally Biased Estimators

2024, Econometric Reviews
(with David M. Kaplan)

published | accepted | code/tex/etc.

We propose simple CIs using estimators that are intentionally biased to reduce MSE (like sivqr/SEE-IVQR). At 95% confidence level, these CIs improve the length and coverage probability compared to the benchmark CI using unbiased estimator.

k-Class Instrumental Variables Quantile Regression

2024, Empirical Economics
(with David M. Kaplan)

published | accepted | code/tex/etc.

We apply k-class estimation to IVQR to reliably reduce median bias for certain choices of k.

Smoothed GMM for quantile models

2019, Journal of Econometrics
(with Luciano de Castro, Antonio Galvao, and David M. Kaplan)

published | accepted | code/tex/etc.

We extend smoothed IVQR estimation (Kaplan and Sun, 2017) to non-iid data, nonlinear and over-identified models, with a quantile Euler equation empirical example.