Dataset Information

A novel nonparametric measure of explained variation for survival data with an easy graphical interpretation.

ABSTRACT: INTRODUCTION:For survival data the coefficient of determination cannot be used to describe how good a model fits to the data. Therefore, several measures of explained variation for survival data have been proposed in recent years. METHODS:We analyse an existing measure of explained variation with regard to minimisation aspects and demonstrate that these are not fulfilled for the measure. RESULTS:In analogy to the least squares method from linear regression analysis we develop a novel measure for categorical covariates which is based only on the Kaplan-Meier estimator. Hence, the novel measure is a completely nonparametric measure with an easy graphical interpretation. For the novel measure different weighting possibilities are available and a statistical test of significance can be performed. Eventually, we apply the novel measure and further measures of explained variation to a dataset comprising persons with a histopathological papillary thyroid carcinoma. CONCLUSION:We propose a novel measure of explained variation with a comprehensible derivation as well as a graphical interpretation, which may be used in further analyses with survival data.

SUBMITTER: Weiß V

PROVIDER: S-EPMC4633600 | biostudies-literature | 2015

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A novel nonparametric measure of explained variation for survival data with an easy graphical interpretation.

Weiß Verena V Schmidt Matthias M Hellmich Martin M

German medical science : GMS e-journal 20151029

<h4>Introduction</h4>For survival data the coefficient of determination cannot be used to describe how good a model fits to the data. Therefore, several measures of explained variation for survival data have been proposed in recent years.<h4>Methods</h4>We analyse an existing measure of explained variation with regard to minimisation aspects and demonstrate that these are not fulfilled for the measure.<h4>Results</h4>In analogy to the least squares method from linear regression analysis we devel ...[more]

PMID: 26550007

Similar Datasets

Project description:BackgroundIn the past decade, the field of molecular biology has become increasingly quantitative; rapid development of new technologies enables researchers to investigate and address fundamental issues quickly and in an efficient manner which were once impossible. Among these technologies, DNA microarray provides methodology for many applications such as gene discovery, diseases diagnosis, drug development and toxicological research and it has been used increasingly since it first emerged. Multiple tools have been developed to interpret the high-throughput data produced by microarrays. However, many times, less consideration has been given to the fact that an extensive and effective interpretation requires close interplay between the bioinformaticians who analyze the data and the biologists who generate it. To bridge this gap and to simplify the usability of such tools we developed Eureka-DMA - an easy-to-operate graphical user interface that allows bioinformaticians and bench-biologists alike to initiate analyses as well as to investigate the data produced by DNA microarrays.ResultsIn this paper, we describe Eureka-DMA, a user-friendly software that comprises a set of methods for the interpretation of gene expression arrays. Eureka-DMA includes methods for the identification of genes with differential expression between conditions; it searches for enriched pathways and gene ontology terms and combines them with other relevant features. It thus enables the full understanding of the data for following testing as well as generating new hypotheses. Here we show two analyses, demonstrating examples of how Eureka-DMA can be used and its capability to produce relevant and reliable results.ConclusionsWe have integrated several elementary expression analysis tools to provide a unified interface for their implementation. Eureka-DMA's simple graphical user interface provides effective and efficient framework in which the investigator has the full set of tools for the visualization and interpretation of the data with the option of exporting the analysis results for later use in other platforms. Eureka-DMA is freely available for academic users and can be downloaded at http://blue-meduza.org/Eureka-DMA.

Dataset Information

A novel nonparametric measure of explained variation for survival data with an easy graphical interpretation.

Publications

A novel nonparametric measure of explained variation for survival data with an easy graphical interpretation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets