I am a Ph.D. candidate in Business Economics at Harvard University, on the 2024-2025 job market. Previously, I worked at the Federal Reserve Bank of New York and studied at Columbia University.
My current research interests are in industrial organization, econometrics, and finance. I also develop statistical software.
You can download my CV here.
Feel free to reach me at jgortmaker@g.harvard.edu. My social media links are in the footer of this page. For inquiries about software, you can contact me directly or use the issue tracker.
Publications
Best Practices for Differentiated Products Demand Estimation with PyBLP [Publication] [Appendix]
with Chris Conlon, November 2020, RAND Journal of Economics, 51(4), 1108-1161
Abstract
Differentiated products demand systems are a workhorse for understanding the price effects of mergers, the value of new goods, and the contribution of products to seller networks. Berry, Levinsohn, and Pakes (1995) provide a flexible random coefficients logit model which accounts for the endogeneity of prices. This article reviews and combines several recent advances related to the estimation of BLP-type problems and implements an extensible generic interface via the PyBLP package. Monte Carlo experiments and replications suggest different conclusions than the prior literature: multiple local optima appear to be rare in well-identified problems; good performance is possible even in small samples, particularly when "optimal instruments" are employed along with supply-side restrictions.
Working Papers
Incorporating Micro Data into Differentiated Products Demand Estimation with PyBLP
with Chris Conlon, Revise & Resubmit at Journal of Econometrics
Abstract
We delineate a general framework for incorporating many types of micro data from summary statistics to full surveys of selected consumers into Berry, Levinsohn, and Pakes (1995)style estimates of differentiated products demand systems. We extend recommended practices for BLP estimation in Conlon and Gortmaker (2020) to the case with micro data and implement them in our open-source package PyBLP. Monte Carlo experiments and empirical examples suggest that incorporating micro data can substantially improve the finite sample performance of the BLP estimator, particularly when using well-targeted summary statistics or "optimal micro moments" that we derive and show how to compute.
Labor Reactions to Credit Deterioration: Evidence from LinkedIn Activity
with Jessica Jeffers and Michael Lee, Reject & Resubmit at Management Science
Abstract
We provide the first analysis of workers' on-the-job networking activity following their firm's credit deterioration. Using high-frequency networking on LinkedIn, we show that workers initiate more connections immediately following adverse credit shocks. We propose a simple model in which workers are driven by concerns about both unemployment and reduced future prospects at their firm. Consistent with this model and distinct from prior work, we find that the stronger response of high-value workers is magnified when the firm is far from bankruptcy. We further show that elevated networking activity is associated with departures and diminished profitability in following years, consistent with on-the-job networking being a source of fragility for firms.
Software
PyBLP: BLP Demand Estimation [Documentation] [Issues]
with Chris Conlon
PyHDFE: High Dimensional Fixed Effect Absorption [Documentation] [Issues]
with Anya Tarascina
Other Writing
Demand Estimation Mixtape Session [Intro] [Day 1] [Exercise 1] [Day 2] [Exercise 2] [Day 3] [Exercise 3]
with Ariel Pakes