Online Program Home
  My Program

Abstract Details

Activity Number: 474 - Nonparametric Density and Variance Estimation
Type: Contributed
Date/Time: Wednesday, August 2, 2017 : 8:30 AM to 10:20 AM
Sponsor: Section on Nonparametric Statistics
Abstract #323942 View Presentation
Title: Orthogonal Series Density Estimation for Complex Surveys
Author(s): Shangyuan Ye* and Ye Liang and Ahmad A. Ibrahim
Companies: Oklahoma State University and Oklahoma State University and Oklahoma State University
Keywords: Nonparametric ; asymptotic ; survey sampling ; orthogonal basis ; mean integrated squared error

Density estimation is an important topic in survey sampling since it summarizes all relevant information about the population of interest. However, the assumption of independent and identically distributed samples are violated when data are sampled from a finite population using a complex sampling design. In this paper, we propose an orthogonal series density estimation (OSDE) for complex surveys. The proposed estimator is design-unbiased and asymptotically design-consistent. The asymptotic normality is studied under both design and combined spaces. We also show the lower bound of minimax mean integrated squared error (MISE) for the proposed estimator. Data driven estimators are proposed and studied via both simulation and real data analysis.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2017 program

Copyright © American Statistical Association