Nonparametric relevance-shifted multiple testing procedures for the analysis of high-dimensional multivariate data with small sample sizes

Zur Kurzanzeige

dc.identifier.uri http://dx.doi.org/10.15488/629
dc.identifier.uri http://www.repo.uni-hannover.de/handle/123456789/653
dc.contributor.author Frömke, C.
dc.contributor.author Hothorn, Ludwig A.
dc.contributor.author Kropf, S.
dc.date.accessioned 2016-11-02T13:36:03Z
dc.date.available 2016-11-02T13:36:03Z
dc.date.issued 2008
dc.identifier.citation Frömke, C.; Hothorn, Ludwig, A.; Kropf, S.: Nonparametric relevance-shifted multiple testing procedures for the analysis of high-dimensional multivariate data with small sample sizes. In: BMC Bioinformatics 9 (2008), 54. DOI. http://dx.doi.org/10.1186/1471-2105-9-54
dc.description.abstract Background: In many research areas it is necessary to find differences between treatment groups with several variables. For example, studies of microarray data seek to find a significant difference in location parameters from zero or one for ratios thereof for each variable. However, in some studies a significant deviation of the difference in locations from zero (or 1 in terms of the ratio) is biologically meaningless. A relevant difference or ratio is sought in such cases. Results: This article addresses the use of relevance-shifted tests on ratios for a multivariate parallel two-sample group design. Two empirical procedures are proposed which embed the relevance-shifted test on ratios. As both procedures test a hypothesis for each variable, the resulting multiple testing problem has to be considered. Hence, the procedures include a multiplicity correction. Both procedures are extensions of available procedures for point null hypotheses achieving exact control of the familywise error rate. Whereas the shift of the null hypothesis alone would give straight-forward solutions, the problems that are the reason for the empirical considerations discussed here arise by the fact that the shift is considered in both directions and the whole parameter space in between these two limits has to be accepted as null hypothesis. Conclusion: The first algorithm to be discussed uses a permutation algorithm, and is appropriate for designs with a moderately large number of observations. However, many experiments have limited sample sizes. Then the second procedure might be more appropriate, where multiplicity is corrected according to a concept of data-driven order of hypotheses. eng
dc.language.iso eng
dc.publisher London : BioMed Central Ltd.
dc.relation.ispartofseries BMC Bioinformatics 9 (2008)
dc.rights CC BY 2.0
dc.rights.uri https://creativecommons.org/licenses/by/2.0/
dc.subject Familywise error rate eng
dc.subject Location parameters eng
dc.subject Multiple testing problems eng
dc.subject Multivariate data eng
dc.subject Parameter spaces eng
dc.subject Second procedures eng
dc.subject Several variables eng
dc.subject Small Sample Size eng
dc.subject Algorithms eng
dc.subject Statistical tests eng
dc.subject analytical error eng
dc.subject article eng
dc.subject data analysis eng
dc.subject mathematical analysis eng
dc.subject mathematical computing eng
dc.subject medical research eng
dc.subject methodology eng
dc.subject microarray analysis eng
dc.subject multivariate analysis eng
dc.subject nonparametric test eng
dc.subject null hypothesis eng
dc.subject rank sum test eng
dc.subject sample size eng
dc.subject simulation eng
dc.subject statistical significance eng
dc.subject algorithm eng
dc.subject biological model eng
dc.subject computer simulation eng
dc.subject DNA microarray eng
dc.subject gene expression profiling eng
dc.subject sample size eng
dc.subject signal processing eng
dc.subject statistical analysis eng
dc.subject statistical model eng
dc.subject Algorithms eng
dc.subject Computer Simulation eng
dc.subject Data Interpretation, Statistical eng
dc.subject Gene Expression Profiling eng
dc.subject Models, Biological eng
dc.subject Models, Statistical eng
dc.subject Multivariate Analysis eng
dc.subject Oligonucleotide Array Sequence Analysis eng
dc.subject Sample Size eng
dc.subject Signal Processing, Computer-Assisted eng
dc.subject.ddc 500 | Naturwissenschaften ger
dc.subject.ddc 570 | Biowissenschaften, Biologie ger
dc.title Nonparametric relevance-shifted multiple testing procedures for the analysis of high-dimensional multivariate data with small sample sizes
dc.type article
dc.type Text
dc.relation.issn 1471-2105
dc.relation.doi http://dx.doi.org/10.1186/1471-2105-9-54
dc.bibliographicCitation.volume 9
dc.bibliographicCitation.firstPage 54
dc.description.version publishedVersion
tib.accessRights frei zug�nglich


Die Publikation erscheint in Sammlung(en):

Zur Kurzanzeige

 

Suche im Repositorium


Durchblättern

Mein Nutzer/innenkonto

Nutzungsstatistiken