B0252
Title: Testing for randomness in a random coefficient autoregression model
Authors: Lorenzo Trapani - Cass Business School (United Kingdom) [presenting]
Lajos Horvath - University of Utah (USA)
Abstract: A test is proposed to discern between an ordinary autoregressive model, and a random coefficient one. To this end, we develop a full-fledged estimation theory for the variances of the idiosyncratic innovation and of the random coefficient, based on a two-stage WLS approach. Our results hold irrespective of whether the series is stationary, nonstationary, or on the boundary between the two regimes. In addition to deriving strong rates of convergence, we also, as a technical by-product, present a complete set of results for the boundary case, providing an almost sure lower bound for the growth rate of the series in this case. Building on these results, we develop a randomised test statistic for the null that the coefficient is random, as opposed to the alternative of an AR(1) model.
Journal