University of Colorado - Boulder
Time Series Econometrics, Econometric Theory
Jonathan Hill received his Ph.D. in economics from the University of Colorado at Boulder in 2001. His early research concerned tests of functional form motivated by interests in perfect tests asymptotically and tests that exploit revealing structure on non-standard spaces; and tail parameter and tail dependence estimation and inference under weak assumptions motivated by new weak limit theory for tail arrays of dependent and non-stationary data. His research has evolved toward robust estimation problems for heavy tailed data, including M-estimation, GMM, and Empirical Likelihood; and robust inference problems including tests of functional form, moment conditions and dependence, with recent extensions to volatility spillover, Expected Shortfall, and Variance Targeting. A key ingredient is standard (Gaussian) weak limit theory for non-standard problems, in this case for tail-weighted arrays of heavy tailed, dependent stochastic functions with imbedded unknown parameters, the foundations of asymptotics for minimum discrepancy estimators.