Search

Abstract: Previous results have indicated that the OLS estimator of the vector of regression coefficients can be nearly as efficient as the best linear unbiased estimator when the regression errors follow a spatial process with root in the vicinity of unity. Such results were derived under the assumption of a symmetric weights matrix, which simplifies the analysis considerably, but is very often not satisfied in applications. This paper provides nontrivial generalizations to the important case of nonsymmetric weights matrices. [Copyright &y& Elsevier]

Abstract: In this paper the effects of temporal aggregation on a class of Markov switching models known as MSG models, are investigated. Mathematical formulae are derived for the first and second moments of an aggregated MSG model. [Copyright &y& Elsevier]

Abstract: In the traditional Box–Jenkins modelling procedure, we use the sample autocorrelation function as a tool for identifying the plausible models for empirical data. In this paper, we consider the sample normalized codifference as a new tool for the preliminary order identification of moving average process with infinite variance. From simulation studies, we find that the proposed method may perform as well as the Rosenfeld''s [1976. Identification of time series with infinite variance. Appl. Statist. 25, 147–153.] method. [Copyright &y& Elsevier]

Abstract: A weakly stationary process with summable partial autocorrelations is proved to have one-sided autoregressive and moving average representations. Sums of autocorrelations and alternating autocorrelations are expressed as products of simple rational functions of partial autocorrelations. A general bound for sums of squared autocorrelations in terms of partial autocorrelations is also obtained. [Copyright &y& Elsevier]

Abstract: This paper extends recent ideas for constructing classes of stationary autoregressive processes of order 1. A Gibbs sampler representation of such processes is extended in a straightforward way to introduce new processes. These maintain a linear expectation property which provides a simple exponential form for the autocorrelation function. [Copyright &y& Elsevier]

Abstract: This paper describes a method of sampling stationary autoregressive models so that they are uniformly distributed in value. A log-Gamma distribution, whose product density is uniformly distributed over , is used to sample partial autocorrelation parameters and obtain the desired result. This method can be used for the empirical evaluation of model selection and parameter estimation criteria. [Copyright &y& Elsevier]

Abstract: This note studies the () spurious regression model for the special case where the weight matrix is normalized and has equal elements, and where the nonstationarity is caused by near unit roots. It shows that spurious spatial regression will not occur in a spatially autoregressive (SAR) model when the spatial weight matrix is row-normalized and has equal weights. In fact, the asymptotic distribution of the OLS estimate will always converge to its true value zero. The only condition required is that the spatial coefficients of the dependent and independent variables be both less than 1, which is a requirement for the SAR model to be an equilibrium model. [ABSTRACT FROM AUTHOR]