Roberto Casarin

Online data processing: comparison of Bayesian regularized particle filters

The aim of this paper is to compare three regularized particle filters in an online data processing context. We carry out the comparison in terms of hidden states filtering and parameters estmation, considering a Bayesian paradigm and a univariate stochastic volatility model. We discuss the use of an improper prior distribution in the initialization of the filtering procedure and show that the Regularized Auxiliary Particle Filter (R-APF) outperforms the Regularized Sequential Importance Sampling (R-SIS) and the Regularized Sampling Importance Resampling (R-SIR).

Italian Equity Funds: Efficiency and Performance Persistence

Have Italian mutual funds been able to generate �extra-return�? Were some of them able to persistently beat the competitors? In this paper we address these questions and provide a detailed and systematic performance and return persistence analysis of the Italian equity mutual funds. We show that, in general, fund managers have not been able to score extra-performances and only few managers had stock picking ability or market timing ability. This evidence is consistent with the market efficiency hypothesis. Moreover, concerning performance persistence, first, we cannot trace out the hot-hand phenomenon on raw returns. The no persistence effect is fairly robust to: the performance measure, the temporal lag and the different methodology employed for testing persistence. Second, there has not been long-run persistence on risk-adjusted returns (we find a weak evidence of the reversal effect). Finally, the past performance displays weak evidence of the hot-hand effect on risk-adjusted returns on four-month using cross-section tests. However, as soon as we analyse yearly intervals any evidence of persistence disappears.

Interacting multiple try algorithms with different proposal distributions

We introduce a new class of interacting Markov chain Monte Carlo (MCMC) algorithms which is designed to increase the efficiency of a modified multiple-try Metropolis (MTM) sampler. The extension with respect to the existing MCMC literature is twofold. First, the sampler proposed extends the basic MTM algorithm by allowing for different proposal distributions in the multiple-try generation step. Second, we exploit the different proposal distributions to naturally introduce an interacting MTM mechanism (IMTM) that expands the class of population Monte Carlo methods and builds connections with the rapidly expanding world of adaptive MCMC. We show the validity of the algorithm and discuss the choice of the selection weights and of the different proposals. The numerical studies show that the interaction mechanism allows the IMTM to efficiently explore the state space leading to higher efficiency than other competing algorithms.

Relative benchmark rating and persistence analysis: Evidence from Italian equity funds

Abstract The recent introduction into the Italian mutual fund market of Morningstar performance rating of private institutions gives rise to the question of what is the relation between this relative benchmark measure and the other traditional performance measures. This paper provides a comprehensive analysis of the relative benchmark performance measure (Morningstar rating) applied to Italian equity funds. It is found that this performance measure is highly correlated with the classical performance measures (Sharpe ratio, Sortino ratio and Treynor ratio) and poorly correlated with the customized benchmark measure (Information ratio). Furthermore, performing a persistence analysis, using non-parametric methods Cross-product Ratio and Chi-squared test, it is observed that only the Morningstar rating measure generates a strong degree of persistence. These results deviate from most European studies, which argue that Italian mutual funds display weak persistence.

Combining Predictive Densities using Nonlinear Filtering with Applications to US Economics Data

Using a Bayesian framework this paper provides a multivariate combination approach to prediction based on a distributional state space representation of predictive densities from alternative models. In the proposed approach the model set can be incomplete. Several multivariate time-varying combination strategies are introduced. In particular, a weight dynamics driven by the past performance of the predictive densities is considered and the use of learning mechanisms. The approach is assessed using statistical and utility-based performance measures for evaluating density forecasts of US macroeconomic time series and of surveys of stock market prices.

Being on the Field When the Game Is Still Under Way. The Financial Press and Stock Markets in Times of Crisis

This paper looks at the relationship between negative news and stock markets in times of global crisis, such as the 2008/2009 period. We analysed one year of front page banner headlines of three financial newspapers, the Wall Street Journal, Financial Times, and Il Sole24ore to examine the influence of bad news both on stock market volatility and dynamic correlation. Our results show that the press and markets influenced each other in generating market volatility and in particular, that the Wall Street Journal had a crucial effect both on the volatility and correlation between the US and foreign markets. We also found significant differences between newspapers in their interpretation of the crisis, with the Financial Times being significantly pessimistic even in phases of low market volatility. Our results confirm the reflexive nature of stock markets. When the situation is uncertain and unpredictable, market behaviour may even reflect qualitative, big picture, and subjective information such as streamers in a newspaper, whose economic and informative value is questionable.

Stochastic Processes in Credit Risk Modelling

In credit risk modelling, jump processes are widely used to de- scribe both default and rating migration events. This work is mainly a review of some basic de nitions and properties of the jump processes intended for a preliminary step before more ad- vanced lectures on credit risk modelling. We focus on the Poisson process and some generalisations, like the compounded and the double stochastic Poisson processes, which are widely used for describing the time-inhomogeneous dynamic either of the default process or of the credit rating transition. As such, much of the material is not new, but focused and organized from a credit risk perspective. Moreover it contains detailed proofs of some funda- mental results. Other original contributions come from examples and simulated studies, which help the reader to better understand the features of the described processes.

Beta Autoregressive Transition Markov-Switching Models for Business Cycle Analysis

We propose a new class of Markov-switching models useful for business cycle analysis, with transition probabilities following independent beta autoregressive processes. We study the effects of the autoregressive dynamics on the regime duration. We propose a full Bayesian inference approach and particular attention is paid to the parameters of the latent beta autoregressive processes. We discuss the choice of the prior distributions and propose a Markov-chain Monte Carlo algorithm for estimating both the parameters and the latent variables. Finally, we provide an application to the Euro area business cycle.

Efficient Gibbs sampling for Markov switching GARCH models

Efficient simulation techniques for Bayesian inference on Markov-switching (MS) GARCH models are developed. Different multi-move sampling techniques for Markov switching state space models are discussed with particular attention to MS-GARCH models. The multi-move sampling strategy is based on the Forward Filtering Backward Sampling (FFBS) approach applied to auxiliary MS-GARCH models. A unified framework for MS-GARCH approximation is developed and this not only encompasses the considered specifications, but provides an avenue to generate new variants of MS-GARCH auxiliary models. The use of multi-point samplers, such as the multiple-try Metropolis and the multiple-trial metropolized independent sampler, in combination with FFBS, is considered in order to reduce the correlation between successive iterates and to avoid getting trapped by local modes of the target distribution. Antithetic sampling within the FFBS is also suggested to further improve the samplers efficiency. The simulation study indicates that the multi-point and multi-move strategies can be more efficient than other MCMC schemes, especially when the MS-GARCH is not strongly persistent. Finally, an empirical application to financial data shows the efficiency and effectiveness of the proposed estimation procedure.

Interactions between eurozone and US booms and busts: A Bayesian panel Markov-switching VAR model

Interactions between the eurozone and US booms and busts and among major eurozone economies are analyzed by introducing a panel Markov-switching VAR model well suitable for a multi-country cyclical analysis. The model accommodates changes in low and high data frequencies and endogenous time-varying transition matrices of the country-specific Markov chains. The transition matrix of each Markov chain depends on its own past history and on the history of the other chains, thus allowing for modelling of the interactions between cycles. An endogenous common eurozone cycle is derived by aggregating country-specific cycles. The model is estimated using a simulation based Bayesian approach in which an effi cient multi-move strategy algorithm is defined to draw common time-varying Markov-switching chains. Our results show that the US and eurozone cycles are not fully synchronized over the 1991-2013 sample period, with evidence of more recessions in the eurozone, in particular during the 90s when the monetary union was planned. Larger synchronization occurs at beginning of the Great Financial Crisis. Shocks affect the US 1-quarter in advance of the eurozone, but these spread very rapidly among economies. There exist reinforcement effects in the recession probabilities and in the probabilities of exiting recessions for both eurozone and US cycles, and substantial differences in the phase transitions within the eurozone. An increase in the number of eurozone countries in recession increases the probability of the US to stay within recession, while the US recession indicator has a negative impact on the probability to stay in recession for eurozone countries. Moreover, turning point analysis shows that the cycles of Germany, France and Italy are closer to the US cycle than other countries. Belgium, Spain, and Germany, provide more timely information on the aggregate recession than Netherlands and France.