
on Econometric Time Series 
By:  Jia Chen; Jiti Gao; Degui Li; Zhengyan Lin 
Abstract:  In this paper, we consider a specification testing problem in nonlinear time series models with nonstationary regressors and propose using a nonparametric kernelbased test statistic. The nullasymptotics for the proposed nonparametric test statistic have been well developed in the existing literature such as Gao et al (2009b) and Wang and Phillips (2012). In this paper, we study the local asymptotics of the test statistic, i.e., the asymptotic properties of the test statistic under a sequence of general nonparametric local alternatives, and show that the asymptotic distribution depends on the asymptotic behaviour of the distance function which is the local deviation from the parametrically specified model in the null hypothesis. In order to implement the proposed test in practice, we introduce a bootstrap procedure to approximate the critical values of the test statistic and establish a novel result of Edgeworth expansion which is used to justify the use of such an approximation. Based on the approximate critical values, we develop a bandwidth selection method, which chooses the optimal bandwidth that maximises the local power of the test while its size is controlled at a given significance level. The local power is defined as the power of the proposed test for a given sequence of local alternatives. Such a bandwidth selection is made feasible by an approximate expression for the local power of the test as a function of the bandwidth. A MonteCarlo simulation study is provided to illustrate the finite sample performance of the proposed test. 
Keywords:  Asymptotic distribution; Edgeworth expansion; local power function; nonlinear time series; quadratic form; size function; specification testing; unit root. 
JEL:  C12 C13 C14 
Date:  2014–09 
URL:  http://d.repec.org/n?u=RePEc:yor:yorken:14/19&r=ets 
By:  Yiannis Karavias; Elias Tzavalis 
Abstract:  Finite T panel data unit root tests allowing for structural breaks, spatial cross section dependence, heteroscedasticity, serial correlation, heterogeneity and nonlinear trends are proposed. The structural breaks can be at known or unknown dates. For the latter, analytic probability density functions of the asymptotic distributions of the tests are provided based on a minimum order statistic. The tests can accommodate general forms of spatial dependence for which the spatial weights matrix does not have to be de?ned due to the utilization of a nonparametric estimator. A set of sufficient conditions which determines admissible deterministic trend functions is also provided. Finally, extensive Monte Carlo experiments show the usefulness of the new tests. 
Keywords:  Panel data; Unit roots; Structural breaks; Spatial dependence; Serial correlation; Fixed T JEL classification: C22, C23 
URL:  http://d.repec.org/n?u=RePEc:not:notgts:14/03&r=ets 
By:  MoralBenito, Enrique; Serven, Luis 
Abstract:  For reason of empirical tractability, analysis of cointegrated economic time series is often developed in a partial setting, in which a subset of variables is explicitly modeled conditional on the rest. This approach yields valid inference only if the conditioning variables are weakly exogenous for the parameters of interest. This paper proposes a new test of weak exogeneity in panel cointegration models. The test has a limiting Gumbel distribution that is obtained by first letting the time dimension of the panel go to infinity and then letting its crosssectional dimension go to infinity. The paper evaluates the accuracy of the asymptotic approximation in finite samples via simulation experiments. Finally, as an empirical illustration, the paper reports tests of weak exogeneity of disposable income and wealth in an aggregate consumption equation. 
Keywords:  Scientific Research&Science Parks,Science Education,Economic Theory&Research,Statistical&Mathematical Sciences,Econometrics 
Date:  2014–09–01 
URL:  http://d.repec.org/n?u=RePEc:wbk:wbrwps:7045&r=ets 
By:  Jos\'e Da Fonseca; Claude Martini 
Abstract:  The aim of this work is to introduce a new stochastic volatility model for equity derivatives. To overcome some of the wellknown problems of the Heston model, and more generally of the affine models, we define a new specification for the dynamics of the stock and its volatility. Within this framework we develop all the key elements to perform the pricing of vanilla European options as well as of volatility derivatives. We clarify the conditions under which the stock price is a martingale and illustrate how the model can be implemented. 
Date:  2014–09 
URL:  http://d.repec.org/n?u=RePEc:arx:papers:1409.5142&r=ets 