
on Econometrics 
By:  Yan Fan; Wolfgang Karl Härdle; Weining Wang; Lixing Zhu 
Abstract:  Quantile regression is in the focus of many estimation techniques and is an important tool in data analysis. When it comes to nonparametric specifications of the conditional quantile (or more generally tail) curve one faces, as in mean regression, a dimensionality problem. We propose a projection based single index model specifi cation. For very high dimensional regressors X one faces yet another dimensionality problem and needs to balance precision vs. dimension. Such a balance may be achieved by combining semiparametric ideas with variable selection techniques. 
Keywords:  Quantile Singleindex Regression, Minimum Average Contrast Estimation, Co VaR estimation, Composite quasimaximum likelihood estimation, Lasso, Model selection 
JEL:  C00 C14 C50 C58 
Date:  2013–02 
URL:  http://d.repec.org/n?u=RePEc:hum:wpaper:sfb649dp2013010&r=ecm 
By:  Matyas Barczy; Leif Doering; Zenghu Li; Gyula Pap 
Abstract:  For an affine two factor model, we study the asymptotic properties of the maximum likelihood and least squares estimators of some appearing parameters in the socalled subcritical (ergodic) case based on continuous time observations. We prove strong consistency and asymptotic normality of the estimators in question. 
Date:  2013–02 
URL:  http://d.repec.org/n?u=RePEc:arx:papers:1302.3451&r=ecm 
By:  Lavergne, Pascal 
Abstract:  In empirical research, one commonly aims to obtain evidence in favor of re strictions on parameters, appearing as an economic hypothesis, a consequence of economic theory, or an econometric modeling assumption. I propose a new theoret ical framework based on the KullbackLeibler information to assess the approximate validity of multivariate restrictions in parametric models. I construct tests that are locally asymptotically maximin and locally asymptotically uniformly most powerful invariant. The tests are applied to three different empirical problems. 
Keywords:  Hypothesis testing, Parametric methods. 
JEL:  C12 C52 
Date:  2013–02 
URL:  http://d.repec.org/n?u=RePEc:tse:wpaper:26789&r=ecm 
By:  Shi, W.; Kleijnen, Jack P.C.; Liu, Zhixue (Tilburg University, Center for Economic Research) 
Abstract:  Abstract: Factor screening searches for the really important inputs (factors) among the many inputs that are changed in a realistic simulation experiment. Sequential bifurcation (SB) is a sequential method that changes groups of inputs simultaneously. SB is the most efficient and effective method if the following assumptions are satisfied: (i) secondorder polynomials are adequate approximations of the input/output functions implied by the simulation model; (ii) the signs of all firstorder effects are known; (iii) if two inputs have no important firstorder effects, then they have no important secondorder effects either (heredity property). This paper examines SB for random simulation with multiple responses (outputs), called multiresponse SB (MSB). This MSB selects groups of inputs such that within a group all inputs have the same sign for a specific type of output, so no cancellation of firstorder effects occurs. MSB also applies Waldâ€™s sequential probability ratio test (SPRT) to obtain enough replicates for correctly classifying a group effect or an individual effect as important or unimportant. MSB enables efficient selection of the initial number of replicates in SPRT. The paper also proposes a procedure to validate the three assumptions of MSB. The performance of MSB is examined through extensive Monte Carlo experiments that satisfy all MSB assumptions, and through a case study representing a logistic system in China; the MSB performance is very promising. 
Keywords:  simulation;design of experiments;statistical analysis 
JEL:  C0 C1 C9 C15 C44 
Date:  2013 
URL:  http://d.repec.org/n?u=RePEc:dgr:kubcen:2013009&r=ecm 
By:  Daria Pus; László Mátyás; Cecilia Hornok 
Abstract:  The paper deals with the problems of formalizing econometric models on firmproduct level trade data sets, or similar economic flows. A multidimensional random effects panel data approach is adopted. Several models are introduced taking into account different types of specific effects, interactions and cross correlations. The respective covariance matrixes are derived, as well as procedures to estimate the unknown variance and covariance components, in order to make the Feasible Generalized Least Squares estimation operational. Whenever possible, the spectral decomposition of the covariance matrixes is also provided to make the estimation procedure simpler to implement. Both balanced and unbalanced data sets are considered. 
Date:  2013–02–21 
URL:  http://d.repec.org/n?u=RePEc:ceu:econwp:2013_2&r=ecm 
By:  T.D. Stanley; Hristos Doucouliagos 
Abstract:  We offer what might be regarded as an alternative approach to the conventional ‘fixedeffects’ and ‘randomeffects’ metaanalysis (MA), weighted least squares metaregression analysis (WLSMRA). Although WLS has been well known for many decades, and its properties are well established, its implications for metaanalysis have yet to be fully explored or appreciated. Our simulations demonstrate that WLSMRA is preferable to both fixed and randomeffects MA whether or not there is ‘excess’ heterogeneity. We show how a generalization of fixedeffects weighted averages is an improvement over randomeffects in those exact cases for which randomeffects metaanalysis is designed. 
Keywords:  metaanalysis, metaregression, weighted least squares, fixedeffects, randomeffects 
Date:  2013–02–23 
URL:  http://d.repec.org/n?u=RePEc:dkn:econwp:eco_2013_1&r=ecm 
By:  Antonio Merlo (Department of Economics, University of Pennsylvania); Thomas R.Palfrey (Division of the Humanities and Social Sciences, California Institute of Technology) 
Abstract:  We conduct a model validation analysis of several behavioral models of voter turnout, using laboratory data. We call our method of model validation concealed parameter recovery, where estimation of a model is done under a veil of ignorance about some of the experimentally controlled parameters — in this case voting costs. We use quantal response equilibrium as the underlying, common structure for estimation, and estimate models of instrumental voting, altruistic voting, expressive voting, and ethical voting. All the models except the ethical model recover the concealed parameters reasonably well. We also report the results of a counterfactual analysis based on the recovered parameters, to compare the policy implications of the different models about the cost of a subsidy to increase turnout. 
Keywords:  Turnout, voting, model validation, parameter recovery, laboratory experiments 
JEL:  D72 C52 C92 
Date:  2013–02–11 
URL:  http://d.repec.org/n?u=RePEc:pen:papers:13012&r=ecm 
By:  Miguel Belmonte (Department of Economics, University of Strathclyde); Gary Koop (Department of Economics, University of Strathclyde) 
Abstract:  This paper investigates the usefulness of switching Gaussian state space models as a tool for implementing dynamic model selecting (DMS) or averaging (DMA)in timevarying parameter regression models. DMS methods allow for model switching, where a different model can be chosen at each point in time. Thus, they allow for the explanatory variables in the timevarying parameter regression model to change over time. DMA will carry out model averaging in a timevarying manner. We compare our exact approach to DMA/DMS to a popular existing procedure which relies on the use of forgetting factor approximations. In an application, we use DMS to select different predictors in an inÃ‚â€¡ation forecasting application. We also compare different ways of implementing DMA/DMS and investigate whether they lead to similar results. 
Keywords:  Model switching, forecast combination, switching state space model, inflÃ‚â€¡ation forecasting 
JEL:  C11 C52 E37 E47 
Date:  2013–01 
URL:  http://d.repec.org/n?u=RePEc:str:wpaper:1302&r=ecm 
By:  Joshua C.C. Chan; Eric Eisenstat 
Abstract:  Empirical work in macroeconometrics has mostly restricted to using VARs, even though there are strong theoretical reasons to consider general VARMAs. This is perhaps because estimation of VARMAs is perceived to be challenging. In this article, we develop a Gibbs sampler for the basic VARMA, and demonstrate how it can be extended to models with stochastic volatility and timevarying parameters. We illustrate the methodology through a macroeconomic forecasting exercise. We show that VARMAs produce better density forecasts than VARs, particularly for short forecast horizons. 
JEL:  C11 C32 C53 
Date:  2013–02 
URL:  http://d.repec.org/n?u=RePEc:acb:cbeeco:2013604&r=ecm 
By:  Gary Koop (Department of Economics, University of Strathclyde) 
Abstract:  This paper discusses the challenges faced by the empirical macroeconomist and methods for surmounting them. These challenges arise due to the fact that macroeconometric models potentially include a large number of variables and allow for time variation in parameters. These considerations lead to models which have a large number of parameters to estimate relative to the number of observations. A wide range of approaches are surveyed which aim to overcome the resulting problems. We stress the related themes of prior shrinkage, model averaging and model selection. Subsequently, we consider a particular modelling approach in detail. This involves the use of dynamic model selection methods with large TVPVARs. A forecasting exercise involving a large US macroeconomic data set illustrates the practicality and empirical success of our approach. 
Keywords:  Bayesian VAR; forecasting; timevarying coefficients; statespace model 
JEL:  C11 C52 E27 E37 
Date:  2013–01 
URL:  http://d.repec.org/n?u=RePEc:str:wpaper:1303&r=ecm 
By:  R\'emy Chicheportiche; Anirban Chakraborti 
Abstract:  Study of recurrences in earthquakes, climate, financial timeseries, etc. is crucial to better forecast disasters and limit their consequences. However, almost all the previous phenomenological studies involved only a longranged autocorrelation function, or disregarded the multiscaling properties induced by potential higher order dependencies. Consequently, they missed the facts that nonlinear dependences do impact both the statistics and dynamics of recurrence times, and that scaling arguments for the unconditional distribution may not be applicable. We argue that copulas is the correct modelfree framework to study nonlinear dependencies in time series and related concepts like recurrences. Fitting and/or simulating the intertemporal distribution of recurrence intervals is very much system specific, and cannot actually benefit from universal features, in contrast to the previous claims. This has important implications in epilepsy prognosis and financial risk management applications. 
Date:  2013–02 
URL:  http://d.repec.org/n?u=RePEc:arx:papers:1302.3704&r=ecm 
By:  Adam Clements (QUT); Yin Liao (QUT) 
Abstract:  Understanding the dynamics of volatility and correlation is a crucially important issue. The literature has developed rapidly in recent years with more sophisticated estimates of volatility, and its associated jump and diffusion components. Previous work has found that jumps at an index level are not related to future volatility. Here we examine the links between cojumps within a group of large stocks, the volatility of, and correlation between their returns. It is found that the occurrence of common, or cojumps between the stocks are unrelated to the level of volatility or correlation. On the other hand, both volatility and correlation are lower subsequent to a cojump. This indicates that cojumps are a transient event but in contrast to earlier research have a greater impact that jumps at an index level. 
Keywords:  Realized volatility, correlation, jumps, cojumps, point process 
JEL:  C22 G00 
Date:  2013–02–06 
URL:  http://d.repec.org/n?u=RePEc:qut:auncer:2013_03&r=ecm 