[Forum SIS] seminario di Carlo Sala a Milano-Bicocca

Fabio Bellini fabio.bellini a unimib.it
Gio 8 Gen 2015 09:23:50 CET


Il giorno martedì 13 gennaio alle ore 14.30 
presso l'Aula Seminari del Dipartimento di 
Statistica e Metodi Quantitativi (DISMEQ), al IV 
piano dell'edificio U7 in piazza dell'Ateneo 
Nuovo, il dott. Carlo Sala, dottorando presso il 
Swiss Finance Institute di Lugano, presenterà un seminario su

A BAYESIAN NON PARAMETRIC ESTIMATION OF THE 
CONDITIONAL PHYSICAL MEASURE AND ITS USE FOR THE 
INVESTIGATION OF THE PRICING KERNEL MONOTONICITY

ABSTRACT
While the neoclassical theory requires the pricing kernel to be a monotonically
decreasing function, recent empirical studies found several violations: at
the extremes as well as in the central part of the function. Since Jackwerth
(2000) this is known as pricing kernel puzzle.
Among the possible reasons of the non-monotonicity there is the low informative
content provided by historical stock returns used for the estimation of the
(by construction) unconditional physical measure. 
Conditionality is of key importance
with respect to the daily volatility.
We propose a new flexible and highly informative non-parametric joint method
to estimate the conditional physical measure. 
Then, we use it to investigate the
pricing kernel monotonicity. Given the problem, a natural approach to exploit
simultaneously multiple data and provide 
statistical inference, is the Dirichlet
process. Calibrating the precision parameter, we empirically mix the two
measures, thus combining the prior forward looking information available from
option data with historical stock returns. We obtain a rich and now conditional
physical measure.
The model is tested using S&P 500 and SPX data from 2002 until 2013.
Results are robust and outperform unconditional methods. Interesting results
are obtained in periods of strong market up/down turns (crisis, volatile days)
(joint work with G. Barone Adesi and A. Mira).


Prof. Fabio Bellini
Department of Statistics and Quantitative Methods
University of Milano-Bicocca
Via Bicocca degli Arcimboldi 8, 20126 Milano
0039-2-64483119
http://www.economia.unimib.it/bellini
http://scholar.google.it/citations?user=P61L8P4AAAAJ&hl=it






Maggiori informazioni sulla lista Sis