Approximate Functional Differencing for Average Effect Estimation

15:40-17:00, Wednesday, April 8, 2026

I-206, Boxue Building

Geert DHAENE is Professor (Emeritus) of Econometrics at KU Leuven. His research lies at the intersection of econometric theory and applied methodology, with a particular emphasis on panel data models, nonlinear estimation, and nuisance parameters. Professor Dhaene's contributions to econometrics are widely recognized. His publications appear in leading journals including Econometrica, The Review of Economic Studies, Journal of Econometrics, Econometric Theory, etc.

We study an iterated bias-correction method for estimating average effects in nonlinear panel-data models with fixed effects. The procedure, termed approximate functional differencing, generates a sequence of bias-corrected estimators that can be iterated arbitrarily many times, including a well-defined limit as the number of iterations grows to infinity. We show that this infinitely iterated estimator can have a remarkably small bias: its asymptotic bias decreases at an exponential rate in the time dimension T. We characterize its large-sample properties and provide sufficient conditions under which the limiting estimator is asymptotically unbiased. Extensive simulations reveal that the iterated corrections deliver substantial finite-sample gains. 

For more information of the seminar, scan the following QR code(s) to join Tencent QQ group (904 544 292) or WeChat group named "IAER Seminar (5)", please.

QQ Group

WeChat Group 

(QR code is valid until April 9, 2026)