Dataset Information

A rank-sum test for clustered data when the number of subjects in a group within a cluster is informative.

ABSTRACT: The Wilcoxon rank-sum test is a popular nonparametric test for comparing two independent populations (groups). In recent years, there have been renewed attempts in extending the Wilcoxon rank sum test for clustered data, one of which (Datta and Satten, 2005, Journal of the American Statistical Association 100, 908-915) addresses the issue of informative cluster size, i.e., when the outcomes and the cluster size are correlated. We are faced with a situation where the group specific marginal distribution in a cluster depends on the number of observations in that group (i.e., the intra-cluster group size). We develop a novel extension of the rank-sum test for handling this situation. We compare the performance of our test with the Datta-Satten test, as well as the naive Wilcoxon rank sum test. Using a naturally occurring simulation model of informative intra-cluster group size, we show that only our test maintains the correct size. We also compare our test with a classical signed rank test based on averages of the outcome values in each group paired by the cluster membership. While this test maintains the size, it has lower power than our test. Extensions to multiple group comparisons and the case of clusters not having samples from all groups are also discussed. We apply our test to determine whether there are differences in the attachment loss between the upper and lower teeth and between mesial and buccal sites of periodontal patients.

SUBMITTER: Dutta S

PROVIDER: S-EPMC4870168 | biostudies-literature | 2016 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A rank-sum test for clustered data when the number of subjects in a group within a cluster is informative.

Dutta Sandipan S Datta Somnath S

Biometrics 20151117 2

The Wilcoxon rank-sum test is a popular nonparametric test for comparing two independent populations (groups). In recent years, there have been renewed attempts in extending the Wilcoxon rank sum test for clustered data, one of which (Datta and Satten, 2005, Journal of the American Statistical Association 100, 908-915) addresses the issue of informative cluster size, i.e., when the outcomes and the cluster size are correlated. We are faced with a situation where the group specific marginal distr ...[more]

PMID: 26575695

Similar Datasets

Project description:BackgroundThe design of long oligonucleotides for spotted DNA microarrays requires detailed attention to ensure their optimal performance in the hybridization process. The main challenge is to select an optimal oligonucleotide element that represents each genetic locus/gene in the genome and is unique, devoid of internal structures and repetitive sequences and its Tm is uniform with all other elements on the microarray. Currently, all of the publicly available programs for DNA long oligonucleotide microarray selection utilize various combinations of cutoffs in which each parameter (uniqueness, Tm, and secondary structure) is evaluated and filtered individually. The use of the cutoffs can, however, lead to information loss and to selection of suboptimal oligonucleotides, especially for genomes with extreme distribution of the GC content, a large proportion of repetitive sequences or the presence of large gene families with highly homologous members.ResultsHere we present the program OligoRankPick which is using a weighted rank-based strategy to select microarray oligonucleotide elements via an integer weighted linear function. This approach optimizes the selection criteria (weight score) for each gene individually, accommodating variable properties of the DNA sequence along the genome. The designed algorithm was tested using three microbial genomes Escherichia coli, Saccharomyces cerevisiae and the human malaria parasite species Plasmodium falciparum. In comparison to other published algorithms OligoRankPick provides significant improvements in oligonucleotide design for all three genomes with the most significant improvements observed in the microarray design for P. falciparum whose genome is characterized by large fluctuations of GC content, and abundant gene duplications.ConclusionOligoRankPick is an efficient tool for the design of long oligonucleotide DNA microarrays which does not rely on direct oligonucleotide exclusion by parameter cutoffs but instead optimizes all parameters in context of each other. The weighted rank-sum strategy utilized by this algorithm provides high flexibility of oligonucleotide selection which accommodates extreme variability of DNA sequence properties along genomes of many organisms.

Dataset Information

A rank-sum test for clustered data when the number of subjects in a group within a cluster is informative.

Publications

A rank-sum test for clustered data when the number of subjects in a group within a cluster is informative.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets