Dataset Information

Using the Bernoulli trial approaches for detecting ordered alternatives.

ABSTRACT:

Background

Diagnostic problems in clinical trials are sometimes ordinal. For example, colon tumor staging was performed according to the TNM classification. However, clinical data are limited by markedly small sample sizes in some stage.

Methods

We propose a distribution-free test for detecting ordered alternatives in a completely randomized design. The new statistic is based on summing all correctly (ascending) ordered samples.

Results

The exact mean and variance of the null distribution are derived and it is shown that this distribution is asymptotically normal. Furthermore, we show using Monte Carlo simulation that the proposed test is a significant improvement over the Terpstra-Magel test. That is, power is decreased where the investigator falsely assumes an a priori ordering relationship.

Conclusions

We conclude that these tests frequently detect an ordered trend when, in fact, one does not exist. However, the new test can reduce the error rate, at least not to the extent in which the Jonckheere-Terpstra test does.

SUBMITTER: Chang CH

PROVIDER: S-EPMC3878968 | biostudies-literature | 2013 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using the Bernoulli trial approaches for detecting ordered alternatives.

Chang Chia-Hao CH Chin Chih-Chien CC Yu Weichieh Wayne WW Huang Ying-Yu YY

BMC medical research methodology 20131205

<h4>Background</h4>Diagnostic problems in clinical trials are sometimes ordinal. For example, colon tumor staging was performed according to the TNM classification. However, clinical data are limited by markedly small sample sizes in some stage.<h4>Methods</h4>We propose a distribution-free test for detecting ordered alternatives in a completely randomized design. The new statistic is based on summing all correctly (ascending) ordered samples.<h4>Results</h4>The exact mean and variance of the nu ...[more]

PMID: 24308700

Similar Datasets

Project description:Microplastics (MPs) can enter the body via plastic products. Given modern plastic exposure, we seek to assess MP exposure in large populations through epidemiological tools. In this quasi-experimental study, every participant filled out a questionnaire, and those who satisfied any of the following requirements were not allowed to continue in the study: Diabetes, ulcerative colitis, Crohn's disease, infectious diseases. Participants in the exposure and control groups were provided three hot meals in disposable plastic tableware (DPT) (n = 30) or non-DPT (n = 30), respectively. After a month of observation, individuals in the exposure group discontinued the three meals provided in DPT (n = 27) for 1 month as the post-exposure group. Each Participant in the three groups received a questionnaire survey and fecal sample collection. We compared the differences in MP levels between different groups and used the Bland-Altman analysis method to evaluate the consistency of the results obtained by different measurement methods. Statistically significant differences in the total quantity (P (0.80 matching degree) = 0.020; P (0.65 matching degree) < 0.001) and types (Polyethylene Terephthalate (EVA) (P = 0.039), Polyethylene Terephthalate (PET) (P = 0.022), Polyvinyl Butyral (PVB) (P = 0.013), Chlorinated Polyethylene (CPE) (P = 0.039), phenolic epoxy resin (P = 0.012)) of MPs were observed between the exposure and post-exposure groups. The Bland-Altman analysis results indicate that the two methods exhibit good consistency in the three groups (control group: mean difference = 0.54, agreement limits (95% CI) = - 0.44 ~ 1.54; exposure group: mean difference = 0.41, agreement limits (95% CI) = - 0.19 ~ 1.01; post-exposure group: mean difference = 0.19, agreement limits (95% CI) = - 0.63 ~ 1.02). The method based on questionnaire surveys can substitute the method of fecal sample detection to evaluate the exposure of MP particles.

Dataset Information

Using the Bernoulli trial approaches for detecting ordered alternatives.

Background

Methods

Results

Conclusions

Publications

Using the Bernoulli trial approaches for detecting ordered alternatives.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets