The Impact of Outliers on the Power of the Randomization Test for Two Independent Groups

被引：1

作者：

Branco, F. ^{[1
]}

Oliveira, T. A. ^{[2
]}

Oliveira, A.

Minder, C. E. ^{[3
]}

机构：

[1] Univ Lusofona, CEPCA, Campo Grande 376, P-1749024 Lisbon, Portugal

[2] Univ Aberta, CEAUL & DCeT, P-1269001 Lisbon, Portugal

[3] Univ Zurich, Horten Ctr, CH-8006 Zurich, Switzerland

来源：

NUMERICAL ANALYSIS AND APPLIED MATHEMATICS ICNAAM 2011: INTERNATIONAL CONFERENCE ON NUMERICAL ANALYSIS AND APPLIED MATHEMATICS, VOLS A-C | 2011年 / 1389卷

关键词：

Outliers; power of tests; randomization tests; independent groups;

D O I：

10.1063/1.3637923

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

In our work we studied the impact of outliers on the power of the randomization tests for two independent groups. Four variables were manipulated: simple size, number of groups with outliers, type of distributions and effect size. To simulate data with outliers Normal contaminated distributions were used. For the simulations, we used R software, namely the package 'nor1mix'. We observed that randomization test loses power for all distributions with outliers when compared with the power achieved with the Gaussian. Our results were illustrated graphically and interpreted. We observed that loses in power are directly related to the magnitude of the outliers and are inversely related to sample size.

引用

页数：4

共 50 条

[1] COMPUTER-PROGRAM FOR A RANDOMIZATION TEST OF A DIFFERENCE BETWEEN INDEPENDENT GROUPS
EDGINGTO.ES
TAERUM, T
PYSH, F
STRAIN, AR
[J]. BEHAVIOR RESEARCH METHODS & INSTRUMENTATION, 1974, 6 (03): : 352 - 353
[2] AS 304 - Fisher's randomization test for two small independent samples
Richards, LE
Byrd, J
[J]. JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES C-APPLIED STATISTICS, 1996, 45 (03) : 394 - 398
[3] On the asymptotic power of a test for detecting outliers
Pagurova, VI
[J]. THEORY OF PROBABILITY AND ITS APPLICATIONS, 1998, 42 (03) : 433 - 443
[4] Randomization test of mean is compuationally inaccessible when the number of groups exceeds two
Cousineau, Denis
[J]. TUTORIALS IN QUANTITATIVE METHODS FOR PSYCHOLOGY, 2011, 7 (01):
[5] Highly efficient algorithms for the exact randomization test of the difference between two independent means
Ferland, Pierre
Laurencelle, Louis
[J]. TUTORIALS IN QUANTITATIVE METHODS FOR PSYCHOLOGY, 2012, 8 (03): : 137 - 150
[6] Properties of a randomization test for multifactor comparisons of groups
Torres, Patricia S.
Quaglino, Marta B.
Pillar, Valerio D.
[J]. JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, 2010, 80 (10) : 1131 - 1150
[7] PROGRAM FOR PITMANS RANDOMIZATION TEST FOR 2 INDEPENDENT SAMPLES
HARLOW, DN
LOWRY, J
[J]. BEHAVIORAL SCIENCE, 1970, 15 (02): : 206 - &
[8] ON RANDOMIZATION DISTRIBUTION AND POWER OF VARIANCE RATIO TEST
ATIQULLAH, M
[J]. JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 1963, 25 (02) : 334 - &
[9] Power analysis for testing two independent groups of likert-type data
Liu, Zun-xiong
Chen, Hao
[J]. PROCEEDINGS OF THE 2015 5TH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCES AND AUTOMATION ENGINEERING, 2016, 42 : 34 - 39
[10] Type I error rates and power of two randomization test procedures for the changing criterion design
Manolov, Rumen
Tanious, Rene
[J]. BEHAVIOR RESEARCH METHODS, 2023, 56 (4) : 3637 - 3657

← 1 2 3 4 5 →