|
on Econometric Time Series |
| By: | Francisco Peñaranda (CEMFI, Centro de Estudios Monetarios y Financieros) |
| Abstract: | Much of the growing literature on tactical and strategic asset allocation uses vector autoregressive models (VAR) for returns and predictors. Since the portfolio advice they generate may be misleading if those models are not an accurate description of reality, we evaluate the implied joint density forecasts of US monthly excess returns on stocks and bonds. From the point of view of an investor who rebalances monthly, a VAR offers a reasonable description of the data, which is not improved upon by richer models. We also study the relevance of considering time-varying risk premia and parameter uncertainty in density forecasts. |
| Keywords: | Density forecasts, parameter uncertainty, portfolio choice, probability integral transform, risk premia. |
| JEL: | G11 C53 |
| Date: | 2004–11 |
| URL: | http://d.repec.org/n?u=RePEc:cmf:wpaper:wp2004_0419&r=ets |
| By: | Javier Alvarez; Manuel Arellano (CEMFI, Centro de Estudios Monetarios y Financieros) |
| Abstract: | We develop likelihood-based estimators for autoregressive panel data models that are consistent in the presence of time series heteroskedasticity. Bias corrected conditional score estimators, random effects maximum likelihood (RML) in levels and first differences, and estimators that impose mean stationarity and considered for AR(p) models with individual effects. We investigate identification under unit roots, and show that RML in levels may achieve substantial efficiency gains relative to estimators from data in differences. In an empirical application, we find evidence against unit roots in individual earnings processes from the PSID and the Spanish section of the European Panel. |
| Keywords: | Autoregressive panel data model, bias corrected score, time series heteroskedasticity, random effects, unit root identification, mean stationarity, individual earnings. |
| JEL: | C23 |
| Date: | 2004–12 |
| URL: | http://d.repec.org/n?u=RePEc:cmf:wpaper:wp2004_0421&r=ets |
| By: | Christian Bauer |
| Abstract: | In this paper we consider the theoretical and empirical relevance of a new family of conditionally heteroskedastic models with a trend dependent conditional variance equation: the Trend-GARCH model. The interest in these models lies in the fact that modern microeco- nomic theory often suggests the connection between the past behavior of time series and the subsequent reaction of market individuals and thereon changes in the future characteristics of the time series. Our results reveal important properties of these models, which are con- sistent with stylized facts in ?financial data sets. They can also be employed for model identifi?cation, estimation, and testing. The em- pirical analysis of a broad variety of asset prices signi?ficantly supports the existence of trend effects. The Trend-GARCH model proves to be superior to alternative models such as EGARCH, AGARCH, or TGARCH in replicating the leverage effect in the conditional variance and in fi?tting the news impact curve. |
| Keywords: | GARCH, trend, volatility, news impact curve |
| JEL: | C22 C52 G12 |
| Date: | 2005–02 |
| URL: | http://d.repec.org/n?u=RePEc:uba:hadfwe:trend-garch-bauer_2005-02&r=ets |
| By: | Xiaohong Chen (Department of Economics, New York University); Yanqin Fan (Department of Economics, Vanderbilt University) |
| Abstract: | This paper studies the estimation of a class of copula-based semiparametric stationary Markov models. These models are characterized by nonparametric invariant (or marginal) distributions and parametric copula functions that capture the temporal dependence of the processes; the implied transition distributions are all semiparametric, and a member in this class can be expressed as a generalized semiparametric regression transformation model. One advantage of this copula approach is to separate out the temporal dependence (such as clustering, tail dependence) from the marginal behavior (such as asymmetry, fat tails) of a time series. We present conditions under which processes generated by models in this class are beta-mixing; naturally, these conditions depend only on the copula specification. Simple estimators of the marginal distribution and the copula parameter are provided, and their asymptotic properties are established under easily verifiable conditions. These results allow us to easily obtain the root-n consistent and asymptotically normal estimators of important features of the transition distribution such as the (nonlinear) conditional moments and conditional quantiles. In addition, the semiparametric conditional quantile estimators are automatically monotonic across quantiles, which is attractive for portfolio conditional value-at-risk calculation. |
| Keywords: | Copula, beta-mixing, semiparametric estimation, parametric bootstrap |
| JEL: | C14 C22 |
| Date: | 2002–10 |
| URL: | http://d.repec.org/n?u=RePEc:van:wpaper:0226&r=ets |