C-statistic: A brief explanation of its construction, interpretation and limitations

A brief explanation, interpretation and limitations of clinical statistics is presented. Model validation has traditionally been performed by splitting the data into a training data set and a test data set, in which an initial prediction model is constructed using the training data, while the accura...

Full description

Saved in:
Bibliographic Details
Published in:European journal of cancer (1990) 2018-02, Vol.90, p.130-132
Main Authors: Caetano, S.J., Sonpavde, G., Pond, G.R.
Format: Article
Language:English
Subjects:
Area Under Curve
Clinical medicine
Data Interpretation, Statistical
Datasets
Humans
Mathematical models
Model accuracy
Models, Statistical
Risk
ROC Curve
Statistical methods
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A brief explanation, interpretation and limitations of clinical statistics is presented. Model validation has traditionally been performed by splitting the data into a training data set and a test data set, in which an initial prediction model is constructed using the training data, while the accuracy of the prediction model is assessed using the test data set. Defined as the most commonly used statistic which measures discrimination, concordance statistic represents the area under the receiver operating characteristic curve, which is constructed by plotting the false positive rate against the true positive rate of the test data set. Concordance statistic must lie between 0.5 to 1.
ISSN:0959-8049
1879-0852
DOI:10.1016/j.ejca.2017.10.027