Bart Keijsers

I am Bart Keijsers, a PhD candidate at the Econometric Institute at the Erasmus School of Economics and Tinbergen Institute, under supervision of Dick van Dijk and Erik Kole, and previously by Bart Diris. I have visited Allan Timmermann at the University of California, San Diego.

My primary research area is applied time series econometrics. My research interests include financial econometrics, state space modeling and Bayesian econometrics. I have applied these methods to credit risk, asset allocation and forecasting macroeconomic data. My previous work has been accepted at the Journal of Applied Econometrics.

In my job market paper, titled "Long-term investing under uncertain parameter instability," I assess the costs of uncertainty regarding parameter instability in return predictability for the long-term investor. I compare different types of time-variation, few breaks versus many breaks. Further, I estimate the break probability rather than assume it ex ante, using a mixture innovation model and Bayesian methodology. I find that the losses from ignoring parameter instability are severe, but the costs of assuming an incorrect type of instability are limited.

You can find my research here, and my CV can be found here.

I will be at the ASSA meeting in Philadelphia, and can be reached at keijsers[at]