This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 457
Type: Topic Contributed
Date/Time: Wednesday, August 4, 2010 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistical Computing
Abstract - #308261
Title: Tests of Goodness-of-Fit Based on Smooth Alternatives to the Quantile Function
Author(s): Olivier Thas*+ and John C.W. Rayner
Companies: Ghent University and University of Newcastle
Address: Coupure Links 653, Gent, International, 9000, Belgium
Keywords: L-moments ; generalised Pareto Distribution ; exponential distribution ; nuisance parameter estimation
Abstract:

Smooth tests of goodness-of fit are traditionally based on smooth alternatives to the hypothesised density function. For many distributions this results in powerful tests which are diagnostic in terms of moment deviations. In this paper we present tests that start from smooth alternatives to the quantile function. These tests are diagnostic in terms of L-moments. Conditions for L-moments to exist, are weaker than for the ordinary moments. This type of construction is thus particularly helpful for distributions for which not all ordinary moments exist. This happens, for example, for the Generalised Pareto Distribution (GPD). After having discussed the construction of the test statistic and its asymptotic null distribution, we present the results of an empirical power study, and we demonstrate the test on the GPD and exponential distribution. We also consider nuisance parameter estimation.


The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2010 program




2010 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.