Abstract
In this paper, we study a kernel estimator of the conditional hazard function when the covariates take values in some abstract function space. The almost completely convergence (with rate) of this estimate is obtained when the sample considered is collected in spatial order with mixing structure. These results are extensions to spatial dependent data of the results given by Ferraty et al. (Rev. Roumaine Math. Pures Appl. 53 (2008), 1-18).