Tim Christensen

Assistant Professor
Department of Economics
New York University

curriculum vitae

Working Papers

Dynamic Models with Robust Decision Makers: Identification and Estimation
We study a class of dynamic models in which the decision maker (DM) is uncertain about the data generating process. As in the literature on robust control, the DM maximizes his or her continuation value under a worst-case model, which lies within a nonparametric neighborhood of a benchmark model. We show that the DM's benchmark model and preference parameters are jointly underidentified. With the benchmark model held fixed, we establish nonparametric identification of the DM's continuation value function and worst-case model and local identification of the DM's preference parameters. We present necessary and sufficient conditions for consistent estimation of the DM's continuation value function. We then discuss estimation of the worst-case model and inference for "yield-like functionals" in robust consumption-investment problems. Time-series properties of the worst-case model in a robust consumption-investment problem are documented and connections are drawn with the literature on macroeconomic uncertainty.

Counterfactual Sensitivity and Robustness
(w/ B. Connault)
We propose a framework to study the sensitivity of counterfactuals with respect to certain distributional assumptions that are commonly made but left unexamined in the background of structural models. Using insights from robust control theory, we deifne a "robustness set" as the set of counterfactuals spanned by the distribution of interest moving in a fully nonparametric neighborhood of its benchmark value while other structural features of the model, such as equilibrium conditions, are maintained. The sets bridge the spectrum from a local analysis based on influence functions to a fully nonparametric analysis. We provide a suitable sampling theory and illustrate our procedure with applications to models of static and dynamic discrete choice.

Published or Forthcoming Papers

‚ÄčMonte Carlo Confidence Sets for Identified Sets
(w/ X. Chen and E. Tamer)
accepted for publication in Econometrica

Optimal Sup-norm Rates and Uniform Inference on Nonlinear Functionals of Nonparametric IV Regression
(w/ X. Chen)
Quantitative Economics, 2018, Vol. 9(1), 39-85
paper, supplement, replication files

Nonparametric Stochastic Discount Factor Decomposition
Econometrica, 2017, Vol. 85(5), 1501-1536
paper, supplement, replication files

Nonparametric Identification of Positive Eigenfunctions
Econometric Theory, 2015, Vol. 31(6), 1310-1330

Optimal Uniform Convergence Rates and Asymptotic Normality for Series Estimators Under Weak Dependence and Weak Conditions
(w/ X. Chen)
Journal of Econometrics, 2015, Vol. 188(2), 447-465

Forecasting Spikes in Electricity Prices
(w/ S. Hurn and K. Lindsay)
International Journal of Forecasting, 2012, Vol. 28(2), 400-411

Detecting Common Dynamics in Transitory Components
(w/ S. Hurn and A. Pagan)
Journal of Time Series Econometrics, 2011, Vol. 3(1), Article 3