Posts by Eva Janssens
New! Efficient Estimation of Nonlinear DSGE Models, w/ Sean McCrary
📄 papers.ssrn.com/sol3/papers....
We propose a broadly applicable computationally efficient method for full-information estimation of nonlinear DSGE models. It avoids two key bottlenecks: global solutions and nonlinear filters.
This approach captures nonlinearities such as state dependence while remaining tractable and fast.
• DMP model: accuracy on par with global methods
• Application: state-dependent monetary policy transmission
Extensions: regime-switching, SV, and heterogeneous agents. Feedback welcome!
Unlike standard approach that separates solution and likelihood evaluation, our method integrates the solution within the filtering step.
How? We construct local linear approximations dynamically along the forecasted state path, enabling likelihood-based inference via a time-varying Kalman filter..
New! Efficient Estimation of Nonlinear DSGE Models, w/ Sean McCrary
📄 papers.ssrn.com/sol3/papers....
We propose a broadly applicable computationally efficient method for full-information estimation of nonlinear DSGE models. It avoids two key bottlenecks: global solutions and nonlinear filters.
rodneywhitecenter.wharton.upenn.edu/2025-summer-...
12 more days to apply to our summer school in structural estimation! It's a hands-on course in which you learn how to do SMM and then work on a problem set with your classmates. Open to PhD students in finance, accounting, econ. And faculty.
Wait, there are people that have zero errors in their latex file?! 🙃
Congratulations!
We propose a double robust Lagrange multiplier (DRLM) test for testing the hypotheses specified on the parameters of interest. The DRLM test is robust to both misspecification and weak identification, which are common in applied work www.econometricsociety.org/publications...
To all job market candidates in macro: University of Copenhagen has a 6 year tenure-track assistant professor position. See more here: econjobmarket.org/positions?show…
If you have any questions, please contact me.
Congratulations!
Very interesting!