Erick W. Rengifo

Multivariate reduced rank regression in non-Gaussian contexts, using copulas

A new procedure is proposed that performs reduced rank regression (RRR) in non-Gaussian contexts based on multivariate dispersion models. Reduced-rank multivariate dispersion models (RR-MDM) generalize RRR to a very large class of distributions, which include continuous distributions like the normal, Gamma, inverse Gaussian, and discrete distributions like the Poisson, the binomial and the negative binomial. A multivariate distribution is created with the help of the Gaussian copula and estimation is performed using maximum likelihood. It is shown how this method can be amended to deal with the case of discrete data. A Monte Carlo simulation shows that the new estimator is more efficient than the traditional Gaussian RRR. In the framework of MDMs a procedure analogous to canonical correlations is introduced, which takes into account the distribution of the data. Finally, the method is applied to the number of trades of five US department stores on the New York Stock Exchange during the year 1999 and determine the existence of a common factor which represents sector specific news. This analysis is helpful in microstructure analysis to identify leaders from the point of view of dissemination of sectorial information.

Intradaily dynamic portfolio selection

A portfolio selection model which allocates a portfolio of currencies by maximizing the expected return subject to Value-at-Risk (VaR) constraint is designed and implemented. Based on an econometric implementation using intradaily data, the optimal portfolio allocation is forecasted at regular time intervals. For the estimation of the conditional variance from which the VaR is computed, univariate and multivariate GARCH models are used. Model evaluation is done using two economic criteria and two statistical tests. The result for each model is given by the best forecasted intradaily investment recommendations in terms of the optimal weights of the currencies in the risky portfolio. The results show that estimating the VaR from multivariate GARCH models improves the results of the forecasted optimal portfolio allocation, compared to using a univariate model.

Intra-daily FX optimal portfolio allocation

We design and implement optimal foreign exchange portfolio allocations. An optimal allocation maximizes the expected return subject to a Value-at-Risk (VaR) constraint. Based on intradaily data, the optimization procedure is carried out at regular time intervals. For the estimation of the conditional variance from which the VaR is computed, we use univariate and multivariate GARCH models. The result for each model is given by the best intradaily investment recommendations in terms of the optimal weights of the currencies in the risky portfolio.

Stochastic Volatility Model with Jumps in Returns and Volatility: An R-Package Implementation

In this chapter we estimate the stochastic volatility model with jumps in return and volatility introduced by [7]. In this model the conditional volatility of returns can not only increase rapidly but also persistently. Moreover, as shown by [8], this new model performs better than previous models presenting almost no misspecification in the volatility process. We implement the model coding the algorithm using R language. We estimate the model parameters and latent variables using FTSE 100 daily returns. The values of some of our estimated parameters are close to values found in previous studies. Also, as expected, our estimated state variable paths show high probabilities of jumps in the periods of financial crisis.

Regime Identification in Limit Order Books

This article develops and implements a new methodology for identifying intraday information regimes in limit order books. Based on Lehmann (2008), in an information regime all the information is trade related and arrives via order ?ow and, the fundamental value that underlines the prices does not change, it is simply translated by the size of the executed market order and the back?lling adjustment. During an information regime the best quotes and the underlying values follow a path de?ned by the limit order book. A change of information regime within a given day is shown to alter the provision of liquidity to the market with consequences for asset prices, trading behavior, and optimal trading strategies. By applying wavelet theory we have developed a methodology that allowed us to clearly identify information regimes. Our results show that information regimes have an impact on price formation and price discovery, including dynamic issues such as the process by which prices come to capture information over time. The discovery and ideate?cation of information regimes essentially uncovers the mechanism by which latent demands are translated into realized prices and volumes. These results empirically support Lehmanni?½s theoretical model.

Investors Facing Risk: Loss Aversion and Wealth Allocation Between Risky and Risk-Free Assets

This paper studies the impact of loss aversion on decisions regarding the allocation of wealth between risky and risk-free assets. We use a Value-at-Risk portfolio model with endogenous desired risk levels that are individually determined in an extended prospect theory framework. This framework allows for the distinction between gains and losses with respect to a subjective reference point as in the original prospect theory, but also for the influence of past performance on the current perception of the risky portfolio value. We show how the portfolio evaluation frequency impacts investor decisions and attitudes when facing financial losses and analyze the role of past gains and losses in the current wealth allocation. The perceived portfolio value exhibits distinct evolutions in two frequency segments delimitated by what we consider to be the optimal evaluation horizon of one year. Our empirical results suggest that previous research relying on VaR underestimates the aversion of real individual investors to financial losses.

Cloud Computing for MATLAB and R Users

Cloud based computing has tremendous potential for academia in general and researchers in particular. The ability to store, read and manipulate large data sets is increasingly important to be on the cutting edge of research. While most researchers have extensive programming skills, they generally are not computer scientists. A number of cloud based, virtual work spaces have been developed which can bring enormous computing advantages over any desktop or laptop. However, the instructions to get up and running in the cloud are often overwhelming, and require a significant investment of time. There is an initial steep learning curve associated with developing a high performance computing environment that several times becomes an obstacle that prevents many to benefit the most from using the cloud. This paper seeks to demystify the process and get the reader up and running very quickly. Once this initial process is over and the reader is proficient on these issues, performing computational chores that would take days on a desktop can be done in minutes. We next show the way the readers can implement their research using two well-known computer programs, MATLAB and R.

Impact of Remittances on Frontier Markets’ Exchange Rate Stability

Most of current research devoted to frontier markets has stressed many different aspects of these economies, ranging from the importance of economic fundamentals to the roles of politics, policies, corruption, and foreign aid. However, little or no attention has been given to the impact of remittances on the local economies in terms of a source of stable funding with clear repercussions on financial and real markets. In this chapter we analyze the impact of remittances on several frontier markets and show their importance in the development and stability of capital markets.

The Individually Acceptable Loss (IAL)

This paper proposes a new, individual measure of market risk, denoted as the individually acceptable loss (IAL). This measure can be used by portfolio managers in order to better meet the individual profiles of their non-professional clients, including psychological traits. It can be easily assessed from general subjective and objective parameters. We formally define the IAL of loss averse investors, who narrowly frame financial investments, and are sensitive to the past performance of their risky portfolio. This individual risk measure is applied to the classic portfolio optimization framework in order to derive the optimal wealth allocation among different financial assets. Our empirical results suggest that previous optimization relying on a portfolio-exogenous VaR-formulation, underestimates the aversion of individual investors towards financial losses.

Investors Facing Risk: Prospect Theory and Non-Expected Utility in Portfolio Selection

This paper focuses on the attitude of non-professional investors towards financial losses and their decisions on wealth allocation, and how these change subject to behavioral factors. Our contribution concerns the integration of behavioral elements into the classic portfolio optimization. Individual perceptions are modeled according to an extended prospect-theory framework: Losses loom larger than gains of the same size (loss aversion) and the past riskyportfolio performance changes the subjective valuation of risky investments. The utility of financial investments is overemphasized (myopia). The portfolio model with individual VaR delivers an optimal wealth assignment between risky and risk-free assets.