Aboubacar Amiri

Learn More
The main purpose of this work is to estimate the regression function of a real random variable with functional explanatory variable by using a recursive nonparametric kernel approach. The mean square error and the almost sure convergence of a family of recursive kernel estimates of the regression function are derived. These results are established with(More)
In this paper, we focus on Radic's definition for the determinant of non-square matrices. We develop some important properties of this determinant. We generalize several classical important determinant identities, including Dodgson's condensation, Cauchy-Binet, and Trahan for non-square matrices. Also, we propose an efficient algorithm with Θ((mn) 2) time(More)
Let (X t , t ∈ N) be a R d-valued α-mixing process, where the X t 's have the same unknown density f. We suggest to estimate f, recursively, from the data X 1 ,. .. , X n. So, we introduce a subfamily of the general recursive kernel estimators initiated by Deheuvels (1974), including the most popular recursive estimators. For this subfamily, we establish(More)
  • 1