We introduce nonlinear panel data models for individual risl management and control. Our approach extends traditional models by allowing for nonlinearities in input variables and unobserved individual heterogeneity with possible temporal dependence. This permits us to develop nonlineat models...

The paper presents a study of dependencies between the autocorrelation function and selected nonlinear transformations of time series. We examine parametric transformations and introduce an analysis of nonlinear canonical correlations. We also propose various methods of testing the...

In a nonlinear framework the magnitude of temporal dependence may depend on the transformation applied to time series. The aim of this paper is to examine in detail various forms of persistence and the corresponding transformations. For multivariate series the persistence analysis is used to...

In order to obtain exact distributional results without imposing restrictive parametric assumptions, various rank counterparts of the Dickey-Fuller statistic are considered. In particular, a rank counterpart of the score statistic is suggested which appears to have attractive theoretical...

We consider a kernel based approach to nonlinear canonical correlation analysis and its implementation for time series. We deduce various diagnostics for reversible processes and gaussian processes. The method is first applied to a stimulated series satisfying a diffusion equation allowing us to...

This paper is interested in small sample properties of the indirect inference procedure which has been previously studied only from an asymptotic point of view. First, we highlight the fact that the Andrews(1993) median-bias correction procedure for autoregresssive parameter of an AR(1) process...

We consider a kernel based approach to nonlinear canonical correlation analysis and its implementation for time series. We deduce a test procedure of the reversibility hypothesis. The method is applied to the analysis of stochastic differential equation from high frequency data on stock returns.

We introduce non-nested hypothesis tests using indirect simulation-based estimation procedures.

We decompose a stationary Markov process (X^t) as: X^t = a^o + [Sommation from j=1 to infinity) a^j Z^(j,t), where the Z^j 's processes admit ARMA specifications. These decompositions are deduced from a nonlinear canonical decomposition of the joint distribution of (X^t, X^(t-1)).