Online Program Home
  My Program

Abstract Details

Activity Number: 402 - Variance, Change Points, and Outliers
Type: Contributed
Date/Time: Tuesday, August 1, 2017 : 2:00 PM to 3:50 PM
Sponsor: Business and Economic Statistics Section
Abstract #323014
Title: Variance Change Point Detection and Its Variations for Robustness
Author(s): Kyungduk Ko*
Companies: Boise State University
Keywords: Change point ; Levene statistic ; Robustness

We propose a method to estimate an unknown variance change point and propose two variations of the resulting statistic for robustness. Levene-type transformations are adopted for the purpose. The null hypothesis distributions of the proposed test statistics are obtained via Monte Carlo simulation. Empirical test sizes and powers are presented under the setting of symmetric, heavy-tailed, and skewed distributions in order to check robustness of the proposed statistics. We apply the proposed method to Dow-Jones Averages.

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

Back to the full JSM 2017 program

Copyright © American Statistical Association