# Jiun-Hua Su 蘇俊華¶

I joined the faculty of the Institute of Economics, Academia Sinica in 2018 as an assistant research fellow after receiving my PhD in Economics from UC Berkeley. My research interest is in Econometrics.

Contact Information

Institute of Economics
Nankang, Taipei, 115 Taiwan
• E-mail: jhsu@econ.sinica.edu.tw

## Working Papers¶

1. Model Selection in Utility-Maximizing Binary Prediction

The semiparametric maximum utility estimation proposed by Elliott and Lieli (2013) can be viewed as cost-sensitive binary classification; thus, its in-sample overfitting issue is similar to that of perceptron learning in the machine learning literature. Based on structural risk minimization, a utility-maximizing prediction rule (UMPR) is constructed to alleviate the in-sample overfitting of the maximum utility estimation. We establish non-asymptotic upper bounds on the difference between the maximal expected utility and the generalized expected utility of the UMPR. Simulation results show that the UMPR with an appropriate data-dependent penalty outweighs some common estimators in binary classification if the conditional probability of the binary outcome is misspecified, or a decision maker's preference is ignored.
2. Counterfactual Inference in Duration Models with Random Censoring

We propose a counterfactual Kaplan-Meier estimator that incorporates exogenous covariates and unobserved heterogeneity of unrestricted dimensionality in duration models with random censoring. Under some regularity conditions, we establish the joint weak convergence of the proposed counterfactual estimator and the unconditional Kaplan-Meier (1958) estimator. Applying the functional delta method, we make inference on the cumulative hazard policy effect, that is, the change of duration dependence in response to a counterfactual policy. We also evaluate the finite sample performance of the proposed counterfactual estimation method in a Monte Carlo study.
3. Testing Monotonicity in a Model with Nonseparable Time-Invariant Heterogeneity

This paper develops a test for structural monotonicity, that is, monotonicity of a structural function in an explanatory variable given any observable covariates and nonseparable time-invariant unobserved heterogeneity. We show that in a two-period panel data model, under some conditions, structural monotonicity implies shape constraints on the joint cumulative distribution function (CDF) of outcome variables conditional on the explanatory variables and covariates over specific regions. These regions are parameterized by a nuisance parameter, which can be consistently estimated. We propose a test for structural monotonicity according to the shape constraints on the conditional joint CDF over the estimated regions, and validate the empirical bootstrap method under some high-level conditions. Some Monte Carlo experiments show that the proposed test can detect departures from structural monotonicity, which are not revealed by some tests for regression monotonicity, for example tests proposed by Ghosal, Sen, and van der Vaart (2000) and Chetverikov (2017).
4. A Multivariate Distribution with Pareto Tails and Pareto Maxima (with Costas Arkolakis and Andrés Rodríguez-Clare)

We present a new multivariate distribution with Pareto distributed tails and maxima. The distribution has a number of properties that make it useful for applied work. Compared to uncorrelated univariate Pareto distributions, the distribution features one additional parameter that governs the covariance of its realizations. We show that this distribution is indeed valid by proving a general result about $n$-increasing functions.