Skip to main content

more options


WORKING PAPERS

Heterogeneous Endogenous Effects in Networks [Job Market Paper]
This paper proposes new spatial autoregression models (SARs) allowing individual specific endogenous effects. This model can be estimated using a two-stage LASSO estimator. Existing SARs implicitly assume that each individual in the network has the same endogenous effects on others. However, some individuals are more influential than others. For example, Banerjee et al. (2013) documents that individuals directly connected with some village leaders are more likely to join a micro-finance program than those connected to someone else. I develop a SAR model that allows for individual-specific endogenous effects and propose a two-stage LASSO (2SLSS) procedure to identify influential individuals in a network. Under an assumption of sparsity only a subset of individuals (which can increase with sample size n) is influential I show that my 2SLSS estimator for individual-specific endogenous effects is consistent and achieves asymptotic normality. I also develop robust inference including uniformly valid confidence intervals. These results also hold in scenarios where the influential individuals are not sparse. I extend the analysis to allow for multiple types of connections (multiple networks), and I show how to use the square-root sparse group LASSO to detect which of the multiple connection type is more influential. Simulation evidence shows that my estimator has a good finite sample performance. Application of my method to the data in Banerjee et al. (2013) shows that my proposed procedure can identify leaders and effective networks.

On Testing Continuity and the Detection of Failures [with Matthew Backus]
Estimation of discontinuities is pervasive in applied economics: from the study of sheepskin effects to prospect theory and bunching" of reported income on tax returns, the salience of discontinuities makes the models that generate them empirically testable. However, detection and identification of those discontinuities typically relies on knowledge of their number, their type, their location, or the underlying functional form. We develop a nonparametric approach to the study of arbitrary discontinuities --point discontinuities as well as jump discontinuities in the nth derivative, where n = 0,1... that does not require ex ante knowledge of their number or location. Our approach exploits the recent development of false discovery rate control methods for LASSO regression as proposed by G'Sell et al. (2015). This framework affords us the ability to construct valid tests for both the null of continuity as well as the significance of any particular discontinuity without the computation of nonstandard distributions. We illustrate the method with a series of Monte Carlo examples and by replicating prior work, e.g. classical regression discontinuity election study (Lee, 2008), Card et al. (2008) and Backus et al.

Local Regression Smoothers with Set Valued Outcome Data [with Qiyu Li, Ilya Molchanov, Francesca Molinari]
We provide statistical results on local linear regression smoothing when the outcome data is set valued and the regressors are exactly measured. We derive the asymptotic properties of our estimator, propose a bias correction method, and adapt results from Beresteanu and Molinari (2008) to obtain point-wise confidence bands that asymptotically cover the functional of interest with probability 1-α. We demonstrate the usefulness of our approach using a novel dataset that follows 132 patients during anti-cancer treatment.

Mostly Harmless Regulation? Health Warnings, Electronic Cigarettes, and Consumer Welfare [with Donald Kenkel , Mike Pesko, Hua Wang]
Electronic cigarettes and other vaping devices provide users with a vapor that contains nicotine without the combustion-generated toxicants in tobacco smoke. Vaping is not harmless but poses much lower risks than smoking. Surveys consistently find that many consumers over-estimate the relative risks of vaping. Some evidence also suggests that vaping devices might be useful for smoking cessation. However, public health advocates are concerned that vaping might lead adolescents to initiate smoking combustible cigarettes. The FDA's Center for Tobacco Products faces difficult tradeoffs to craft electronic-cigarette regulations that do more good than harm. This paper contributes new evidence on some of the tradeoffs involved in regulating electronic cigarettes. We analyze stated preference data from an on-line discrete choice experiment where smokers made hypothetical choices between cigarettes, a nicotine-replacement product, and electronic cigarettes. The attributes of the electronic cigarette were varied experimentally and included price, health warnings, and the availability of multiple flavors. We use the data to estimate the parameters of a random utility-maximization model by mixed logit (random coefficients).

The Role of External Referrals in Hiring: Evidence from Judicial Law Clerks [with Kyle Rozema]
We study the influence of external referrals in the hiring process by estimating a discrete choice hiring model that treats applicants as a differentiated products. We posit that referrals can provide better information about the same attributes of an applicant as a public signal, and hypothesize that referrals aid the hiring process by reducing the extent to which organizations need to rely on public signals. We find empirical support for our hypothesis in the context of Supreme Court law clerks using a rare data set that identifies all potential applicants and establishes ties between the hiring managers and applicants' referrals.


Contact Information

Sida Peng

Address:
Department of Economics
429 Uris Hall
Cornell University
Ithaca, NY 14853

E-mail:
sp947@cornell.edu

Phone:
(434) 249-5434