Power maps in goodness-of-fit testing

For classical goodness-of-fit tests as well as for their modified versions in case of Type-II right censored data, results of a simulation study are presented, where the powers of the tests under consideration against beta alternatives are illustrated in informative, user-oriented plots that offer t...

Full description

Saved in:
Bibliographic Details
Published in:Computational statistics 2013-06, Vol.28 (3), p.1365-1382
Main Authors: Fischer, T., Kamps, U.
Format: Article
Language:English
Subjects:
Algorithms
Beta
Computation
Computational mathematics
Computer simulation
Decomposition
Economic Theory/Quantitative Economics/Mathematical Methods
Hypotheses
Mathematical analysis
Mathematical models
Mathematics and Statistics
Monte Carlo simulation
Original Paper
Probability and Statistics in Computer Science
Probability Theory and Stochastic Processes
Random variables
Statistical tests
Statistics
Studies
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:For classical goodness-of-fit tests as well as for their modified versions in case of Type-II right censored data, results of a simulation study are presented, where the powers of the tests under consideration against beta alternatives are illustrated in informative, user-oriented plots that offer the possibility to directly choose the best test statistic in a concrete situation, when some prior belief about the alternative is available. The behavior of powers of respective statistical tests as functions of beta parameters is examined and discussed.
ISSN:0943-4062
1613-9658
DOI:10.1007/s00180-012-0361-x