Optimal subsampling design for polynomial regression in one covariate

Abstract Improvements in technology lead to increasing availability of large data sets which makes the need for reduction and informative subsamples ever more important. In this paper we construct D -optimal subsampling designs polynomial regression one covariate invariant distributions covariate. We study quadratic closely specific distributions. particular make statements on shape resulting optimal effect subsample size design. To illustrate advantage examine efficiency uniform random subsampling.