Factor Models with Downside Risk

Seminar abstract

The paper presented proposes a conditional model of asset returns in the presence of common factors and downside risk.

Specifically, generalising existing latent factor models in three ways;

1. allowing for downside risk via a threshold specification which allows for the estimation of the (usually set a priori) 'disappointment' event,
2. permitting different factor structures (and number of factors) in different regimes,
3. show how to recover the observable factors risk premia from the estimated latent ones in different regimes.

The usefulness of this generalised model is illustrated through two applications to low-dimensional, medium-sized, and large cross-sections of asset returns.

Booking

This seminar is free to attend with no need to book in advance. 

Speaker bio

Lorenzo Trapani is a Professor of Econometrics at the University of Nottingham, where he is also Director of the Granger Centre for Time Series Econometrics.

He was previously Professor at Cass Business School.

Professor Trapani's main research interests are in econometric theory and statistics, including;

• large factor models
• randomised tests
• the change point problem
• panel data
• cointegration and aggregation
• the random coefficient autoregressive model

His works have been published in the Journal of the American Statistical Association, Journal of Econometrics and Econometric Theory.