Asymptotic properties of LSE of regression coefficients on singular random fields observed on a sphere

We present some upper bounds on the rate of convergence in the central limit theorem for normalized least square estimates (LSE) in a spherical regression model with long range dependence (LRD) stationary errors. The used method is based on the asymptotic analysis of orthogonal expansion of non-linear functionals of homogeneous isotropic Gaussian random fields and on the Kolmogorov distance. The theory have many applications in science for instance in evaluating the COBE data.