Mardi | 2015-05-26
Sully 5, 16h-17h20

Nicolas DEBARSY – Cem ERTUR – Manuel RUIZ-MARIN

In this paper we propose several nonparametric spatial independence tests based on runs. The tests can be applied to quantitative or categorical data and are able to detect linear and nonlinear spatial structure. With a Monte Carlo experiment we show the size and power performance of the statistic under linear and nonlinear data generating process. The results of our test is also compared to other statistics like Moran’s I and the Brett and Pinkse test for spatial dependence.