Speed of Convergence in Density Estimation by Delta Sequence and Estimation of Mode
A. K. Basu, Dillip Kumar Sahoo · Calcutta Statistical Association Bulletin · 1985
Given a sequence of i.i.d. random variables the speed of local as well as global convergence rates of delta sequence type estimators of their common density function, its derivative and its mode is studied. This throws light on the usefulness of such estimators. The method of estimation based on delta sequences has been used because it generalizes many of the well known methods for such problems viz. the Kernel method proposed by Parzen (1962), orthogonal series method used by Schwartz (1967), etc.