nep-ecm New Economics Papers
on Econometrics
Issue of 2007‒04‒28
sixteen papers chosen by
Sune Karlsson
Orebro University

  1. Bayesian Estimation of the Markov-Switching GARCH(1,1) Model with Student-t Innovations By David Ardia
  2. Dynamic Modeling of Large Dimensional Covariance Matrices By Valeri Voev
  3. How to Attain Minimax Risk with Applications to Distribution-Free Nonparametric Estimation and Testing By Karl H. Schlag
  4. Unbiased covariance estimation with interpolated data By Taro Kanatani; Roberto Reno'
  5. A Generalized ARFIMA Process with Markov-Switching Fractional Differencing Parameter By Wen-Jen Tsay; Wolfgang Härdle
  6. An Inflated Multivariate Integer Count Hurdle Model: An Application to Bid and Ask Quote Dynamics By Katarzyna Bien; Ingmar Nolte; Winfried Pohlmeier
  7. Modelling the reporting discrepancies in bilateral data By Arie ten Cate
  8. Online Forecast Combination for Dependent Heterogeneous Data By Sancetta, A.
  9. Rational reconstruction of frailty-based mortality models by a generalisation of Gompertz' law of mortality By W.J. Willemse; R. Kaas
  10. Markov switching GARCH models of currency turmoil in Southeast Asia By Celso Brunetti; Roberto S. Mariano; Chiara Scotti; Augustine H.H. Tan
  11. Panel Intensity Models with Latent Factors: An Application to the Trading Dynamics on the Foreign Exchange Market¤ By Ingmar Nolte; Valeri Voev
  12. Hypothetical bias in choice experiments: Within versus between subject tests By Johansson-Stenman, Olof; Svedsäter, Henrik
  13. Modeling the distribution of credit losses with observable and latent factors By Gabriel Jiménez; Javier Mencía
  14. Mixture Models of Choice Under Risk By Anna Conte; John D Hey; Peter G Moffatt
  15. A forewarning indicator system for financial crises: the case of six Central and Eastern European countries By Irène Andreou; Gilles Dufrénot; Alain Sand-Zantman; Aleksandra Zdzienicka-Durand
  16. HIV/AIDS and Poverty in South Africa: a Bayesian Estimation By Fabrice Murtin; Federica Marzo

  1. By: David Ardia (Department of Quantitative Economics)
    Abstract: This article proposes the Bayesian estimation of the MSGARCH model with Student-t innovations. We introduce a new MCMC scheme which generates the GARCH parameters by block, the vector of state variables in a multi-move manner and the degrees of freedom parameter of the Student-t distribution using an efficient rejection technique. Our methodology is fully automatic and avoids the time-consuming and difficult task of choosing and tuning a sampling algorithm. As an application, we fit a single-regime GARCH model and a MSGARCH model to SMI log-returns. We use the random permutation sampler to find suitable identification constraints for the MSGARCH model and show the presence of two distinct volatility regimes in the time series. By using the Deviance information criterion and estimating the model likelihoods we show the in-sample superiority of the MSGARCH model. Finally, we test the forecasting performance of the competing models based on the VaR and document the superiority of the Markov-switching specification.
    Keywords: Bayesian;MCMC;Markov-switching;HMM;GARCH;DIC;Marginal likelihood;Model likelihood;VaR;SMI
    JEL: C11 C13 C15 C22 C52 C53
    Date: 2007–04–12
  2. By: Valeri Voev (University of Konstanz)
    Abstract: Modelling and forecasting the covariance of financial return series has always been a challange due to the so-called "curse of dimensionality". This paper proposes a methodology that is applicable in large dimensional cases and is based on a time series of realized covariance matrices. Some solutions are also presented to the problem of non-positive definite forecasts. This methodology is then compared to some traditional models on the basis of its forecasting performance employing Diebold-Mariano tests. We show that our approach is better suited to capture the dynamic features of volatilities and covolatilities compared to the sample covariance based models.
    Date: 2007–02–01
  3. By: Karl H. Schlag
    Abstract: We show how to a derive exact distribution-free nonparametric results for minimax risk when underlying random variables have known finite bounds and means are the only parameters of interest. Transform the data with a randomized mean preserving transformation into binary data and then apply the solution to minimax risk for the case where random variables are binary valued. This shows that minimax risk is attained by a linear strategy and the the set of binary valued distributions contains a least favorable prior. We apply these results to statistics. All unbiased symmetric non-randomized estimates for a function of the mean of a single sample are presented. We find a most powerful unbiased test for the mean of a single sample. We present tight lower bounds on size, type II error and minimal accuracy in terms of expected length of confidence intervals for a single mean and for the difference between two means. We show how to transform the randomized tests that attain the lower bounds into non-randomized tests that have at most twice the type I and II errors. Relative parameter efficiency can be measured in finite samples, in an example on anti-selfdealing indices relative (parameter) efficiency is 60% as compared to the tight lower bound. Our method can be used to generate distribution-free nonparametric estimates and tests when variance is the only parameter of interest. In particular we present a uniformly consistent estimator of standard deviation together with an upper bound on expected quadratic loss. We use our estimate to measure income inequality.
    Keywords: exact, distribution-free, nonparametric inference, finite sample theory
    JEL: C13 C12 C44
    Date: 2007
  4. By: Taro Kanatani; Roberto Reno'
    Abstract: We study covariance estimation when compelled to use evenly spaced data which have already been manipulated by previous-tick interpolation. We propose an un- biased covariance estimator, which is designed to correct for the two biases arising because of the interpolation: non-synchronous trading and zero-return bias. We show how these sources make usual realized covariance estimators biased, and that the traditional lead-lag modification does not correct these biases completely. The proposed estimator is also proved to be consistent with the Hayashi and Yoshida (2005)’s unbiased estimator under extremely high frequency situation. We illustrate the potential advantages of the method with both simulated and actual data
    Keywords: Realized covariance; Previous tick interpolation; Epps effect; Nonsynchronous trading; Bias-correction
    JEL: C14 C32 C63
    Date: 2007–04
  5. By: Wen-Jen Tsay; Wolfgang Härdle
    Abstract: We propose a general class of Markov-switching-ARFIMA processes in order to combine strands of long memory and Markov-switching literature. Although the coverage of this class of models is broad, we show that these models can be easily estimated with the DLV algorithm proposed. This algorithm combines the Durbin-Levinson and Viterbi procedures. A Monte Carlo experiment reveals that the finite sample performance of the proposed algorithm for a simple mixture model of Markov-switching mean and ARFIMA(1, d, 1) process is satisfactory. We apply the Markov-switching-ARFIMA models to the U.S. real interest rates, the Nile river level, and the U.S. unemployment rates, respectively. The results are all highly consistent with the conjectures made or empirical results found in the literature. Particularly, we confirm the conjecture in Beran and Terrin (1996) that the observations 1 to about 100 of the Nile river data seem to be more independent than the subsequent observations, and the value of differencing parameter is lower for the first 100 observations than for the subsequent data.
    Keywords: Markov chain; ARFIMA process; Viterbi algorithm; Long memory.
    JEL: C14 C22 C32 C52 C53 G12
    Date: 2007–04
  6. By: Katarzyna Bien (University of Konstanz); Ingmar Nolte (University of Konstanz); Winfried Pohlmeier (University of Konstanz)
    Abstract: In this paper we develop a model for the conditional inflated multivariate density of integer count variables with domain Zn. Our modelling framework is based on a copula approach and can be used for a broad set of applications where the primary characteristics of the data are: (i) discrete domain, (ii) the tendency to cluster at certain outcome values and (iii) contemporaneous dependence. These kind of properties can be found for high or ultra-high frequent data describing the trading process on financial markets. We present a straightforward method of sampling from such an inflated multivariate density through the application of an Independence Metropolis-Hastings sampling algorithm. We demonstrate the power of our approach by modelling the conditional bivari- ate density of bid and ask quote changes in a high frequency setup. We show how to derive the implied conditional discrete density of the bid-ask spread, taking quote clusterings (at multiples of 5 ticks) into account.
    Keywords: Multivariate Discrete Distributions, Conditional Inflation, Copula Functions, Truncations, Metropolized-Independence Sampler
    JEL: G10 F30 C30
    Date: 2007–03–28
  7. By: Arie ten Cate
    Abstract: The discrepancies in reported bilateral statistical data ("mirror data") are used to estimate the accuracy of the reporters. The estimated accuracies are to be used to compute optimal combinations of mirror data. <P> Two models of the discrepancies are presented: (a) unbiased reporting with inaccurate reporters having a large variance, and (b) biased reporting with inaccurate reporters having a large bias (either positive or negative). Estimation methods are least squares regression and maximum likelihood. <P> A numerical illustration is given, using data of the international trade in services. It is shown how to judge the two models empirically. <P> Research has been continued after the publication. In particular about the maximum likelihood estimation of the variance model.
    Keywords: discrepancies; mirror; mirror data; bilateral; international trade; services; GTAP; GAMS
    JEL: C82
    Date: 2007–04
  8. By: Sancetta, A.
    Abstract: This paper studies a procedure to combine individual forecasts that achieve theoretical optimal performance. The results apply to a wide variety of loss functions and no conditions are imposed on the data sequences and the individual forecasts apart from a tail condition. The theoretical results show that the bounds are also valid in the case of time varying combination weights, under specific conditions on the nature of time variation. Some experimental evidence to confirm the results is provided.
    Keywords: Forecast Combination, Model Selection, Multiplicative Update, Non-asymptotic Bound, On-line Learning.
    JEL: C53 C14
    Date: 2007–04
  9. By: W.J. Willemse; R. Kaas
    Abstract: A generalisation of Gompertz' distribution is proposed, and it is shown that continuous heterogeneous mortality models with Gamma distributed frailty have lifetime random variables distributed as the difference of two such generalised Gompertz random variables. With this result, limitations of existing frailty-based mortality models are identified. The approach taken in this paper allows the frailty distribution to be interpreted as a lifetime reduction distribution and enables application of heterogeneous survival models with a stronger relation to empirically identifiable concepts.
    Keywords: Heterogeneous mortality models; Frailty models; Gompertz distribution; Identifiability.
    JEL: C16 J11
    Date: 2007–04
  10. By: Celso Brunetti; Roberto S. Mariano; Chiara Scotti; Augustine H.H. Tan
    Abstract: This paper analyzes exchange rate turmoil with a Markov Switching GARCH model. We distinguish between two different regimes in both the conditional mean and the conditional variance: "ordinary" regime, characterized by low exchange rate changes and low volatility, and "turbulent" regime, characterized by high exchange rate movements and high volatility. We also allow the transition probabilities to vary over time as functions of economic and financial indicators. We find that real effective exchange rates, money supply relative to reserves, stock index returns, and bank stock index returns and volatility contain valuable information for identifying turbulence and ordinary periods.
    Date: 2007
  11. By: Ingmar Nolte (University of Konstanz); Valeri Voev (University of Konstanz)
    Abstract: We develop a panel intensity model, with a time varying latent factor, which captures the influence of unobserved time effects and allows for correlation across individuals. The model is designed to analyze individual trading behavior on the basis of trading activity datasets, which are characterized by four dimensions: an irregularly-spaced time scale, trading activity types, trading instruments and investors. Our approach extends the stochastic conditional intensity model of Bauwens & Hautsch (2006) to panel duration data. We show how to estimate the model parameters by a simulated maximum likelihood technique adopting the efficient importance sampling approach of Richard & Zhang (2005). We provide an application to a trading activity dataset from an internet trading platform in the foreign exchange market and we find support for the presence of behavioral biases and discuss implications for portfolio theory.
    Keywords: Trading Activity Datasets, Panel Intensity Models, Latent Factors, Efficient Importance Sampling, Behavioral Finance
    JEL: G10 F31 C32
    Date: 2007–02–28
  12. By: Johansson-Stenman, Olof (Department of Economics, School of Business, Economics and Law, Göteborg University); Svedsäter, Henrik (Department of Psychology, Göteborg University)
    Abstract: A choice experiment eliciting environmental values is set up in order to test for hypothetical bias based on both within and between sample designs. A larger hypothetical bias was found in the latter case, which explains parts of the previous diverging results in the literature. People seem to prefer to do what they say they would do.<p>
    Keywords: Stated-preference methods; choice experiment; hypothetical bias; internal consistency; non-market valuation;
    JEL: C91 Q28
    Date: 2007–04–20
  13. By: Gabriel Jiménez (Banco de España); Javier Mencía (Banco de España)
    Abstract: This paper develops a flexible and computationally efficient model to estimate the credit loss distribution of the loans in a banking system. We consider a sectorial structure, where default frequencies and the total number of loans are allowed to depend on macroeconomic conditions as well as on unobservable credit risk factors, which can capture contagion effects between sectors. In addition, we also model the distributions of the Exposure at Default and the Loss Given Default. We apply our model to the Spanish credit market, where we find that sectorial default frequencies are affected by a persistent latent factor. Finally, we also identify the potentially riskier sectors and perform stress tests.
    Keywords: credit risk, probability of default, loss distribution, stress test, contagion
    JEL: G21 E32 E37
    Date: 2007–04
  14. By: Anna Conte; John D Hey; Peter G Moffatt
    Abstract: This paper is concerned with estimating preference functionals for choice under risk from the choice behaviour of individuals. We start from the observation that there is heterogeneity in behaviour between individuals and within individuals. By ‘heterogeneity between individuals’ we mean that people are different, not only in terms of which type of preference functional that they have, but also in terms of their parameters for these functionals. By ‘heterogeneity within individuals’ we mean that behaviour may be different even by the same individual for the same choice problem. Given the heterogeneity between individuals, the assumption of a ‘representative agent’ preference functional to represent the preference functional of all individuals may well lead to biased estimates. Given the heterogeneity within individuals, we should think carefully about the source of this heterogeneity and model it appropriately, for otherwise we get biased estimates. We propose solutions to both of these problems, concentrating particularly, but not exclusively, on using a Mixture Model to capture the heterogeneity of preference functionals across individuals.
    Keywords: errors, expected utility theory, experimental economics, maximum simulated likelihood, mixture models, preference functionals, risky choice, rank dependent expected utility theory, unobserved heterogeneity
    JEL: C15 C29 C51 C87 C91 D81
    Date: 2007–04
  15. By: Irène Andreou (GATE - Groupe d'analyse et de théorie économique - [CNRS : UMR5824] - [Université Lumière - Lyon II] - [Ecole Normale Supérieure Lettres et Sciences Humaines]); Gilles Dufrénot (GREQAM - Groupement de Recherche en Économie Quantitative d'Aix-Marseille - [Université de la Méditerranée - Aix-Marseille II][Université de droit, d'économie et des sciences - Aix-Marseille III] - [Ecole des Hautes Etudes en Sciences Sociales]); Alain Sand-Zantman (GATE - Groupe d'analyse et de théorie économique - [CNRS : UMR5824] - [Université Lumière - Lyon II] - [Ecole Normale Supérieure Lettres et Sciences Humaines]); Aleksandra Zdzienicka-Durand (GATE - Groupe d'analyse et de théorie économique - [CNRS : UMR5824] - [Université Lumière - Lyon II] - [Ecole Normale Supérieure Lettres et Sciences Humaines])
    Abstract: We propose a measure of the probability of crises associated with an aggregate indicator, where the percentage of false alarms and the proportion of missed signals can be combined to give an appreciation of the vulnerability of an economy. In this perspective, the important issue is not only to determine whether a system produces true predictions of a crisis, but also whether there are forewarning signs of a forthcoming crisis prior to its actual occurrence. To this end, we adopt the approach initiated by Kaminsky, Lizondo and Reinhart (1998), analyzing each indicator and calculating each threshold separately. We depart from this approach in that each country is also analyzed separately, permitting the creation of a more “custom-made” early warning system for each one.
    Keywords: composite indicator ; currency crisis ; early warning system
    Date: 2007–04–19
  16. By: Fabrice Murtin (GREDI, Université de Sherbrooke); Federica Marzo (CREST, INSEE)
    Abstract: In this paper we assess the causal impact of HIV/AIDS on monetary poverty using a panel data-set from South Africa and modeling the consequences of the illness on both earnings and transfers. Two major econometric problems are likely to bias the estimation: endogeneity of the HIV/AIDS dummy variable, and autoselection of the individuals participating to the labour market or to transfers networks. We solve both of them by proposing an original framework where we include correlated fixed-effects both in the level and the participation equations, which are estimated simultaneously with original Bayesian methods. The procedure is tested and very well-behaved. Splitting the sample into urban and rural population, we show that HIV/AIDS has a significant but moderate impact on poverty for urban population, because transfers partly compensate the fall of earnings entailed by the decrease in labour market participation. On the contrary, HIV/AIDS has an important impact on poverty for the rural population because it causes a fall of transfers. Surprisingly the effect on earnings is not significant . We argue that those results can be explained by the existence of an efficient public safety net in urban settings, while in contrast private transfers are subject to moral hazard and imperfect commitment that characterize risk-sharing in rural settings.
    Keywords: DHIV/AIDS, MCMC, Selection Models
    JEL: C3 D1 I1
    Date: 2007

This nep-ecm issue is ©2007 by Sune Karlsson. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.