An Information-Theoretic Measure for Balance Assessment in Comparative Clinical Studies

Limitations of statistics currently used to assess balance in observation samples include their insensitivity to shape discrepancies and their dependence upon sample size. The Jensen−Shannon divergence (JSD) is an alternative approach to quantifying the lack of balance among treatment grou...

Full description

Bibliographic Details
Main Authors:	Jarrod E. Dalton, William A. Benish, Nikolas I. Krieger
Format:	Article
Language:	English
Published:	MDPI AG 2020-02-01
Series:	Entropy
Subjects:	balance jensen–shannon divergence observational study relative entropy selection bias
Online Access:	https://www.mdpi.com/1099-4300/22/2/218

id	doaj-a69d796fcf36419b956e9118f76b9de0
record_format	Article
spelling	doaj-a69d796fcf36419b956e9118f76b9de02020-11-25T02:20:56ZengMDPI AGEntropy1099-43002020-02-0122221810.3390/e22020218e22020218An Information-Theoretic Measure for Balance Assessment in Comparative Clinical StudiesJarrod E. Dalton0William A. Benish1Nikolas I. Krieger2Department of Quantitative Health Sciences, Cleveland Clinic, Cleveland Clinic Lerner College of Medicine at Case Western Reserve University, 9500 Euclid Avenue, Cleveland, OH 44126, USADepartment of Internal Medicine, Case Western Reserve University, Cleveland, OH 44106, USADepartment of Quantitative Health Sciences, Cleveland Clinic, Cleveland Clinic Lerner College of Medicine at Case Western Reserve University, 9500 Euclid Avenue, Cleveland, OH 44126, USALimitations of statistics currently used to assess balance in observation samples include their insensitivity to shape discrepancies and their dependence upon sample size. The Jensen−Shannon divergence (JSD) is an alternative approach to quantifying the lack of balance among treatment groups that does not have these limitations. The JSD is an information-theoretic statistic derived from relative entropy, with three specific advantages relative to using standardized difference scores. First, it is applicable to cases in which the covariate is categorical or continuous. Second, it generalizes to studies in which there are more than two exposure or treatment groups. Third, it is decomposable, allowing for the identification of specific covariate values, treatment groups or combinations thereof that are responsible for any observed imbalance.https://www.mdpi.com/1099-4300/22/2/218balancejensen–shannon divergenceobservational studyrelative entropyselection bias
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Jarrod E. Dalton William A. Benish Nikolas I. Krieger
spellingShingle	Jarrod E. Dalton William A. Benish Nikolas I. Krieger An Information-Theoretic Measure for Balance Assessment in Comparative Clinical Studies Entropy balance jensen–shannon divergence observational study relative entropy selection bias
author_facet	Jarrod E. Dalton William A. Benish Nikolas I. Krieger
author_sort	Jarrod E. Dalton
title	An Information-Theoretic Measure for Balance Assessment in Comparative Clinical Studies
title_short	An Information-Theoretic Measure for Balance Assessment in Comparative Clinical Studies
title_full	An Information-Theoretic Measure for Balance Assessment in Comparative Clinical Studies
title_fullStr	An Information-Theoretic Measure for Balance Assessment in Comparative Clinical Studies
title_full_unstemmed	An Information-Theoretic Measure for Balance Assessment in Comparative Clinical Studies
title_sort	information-theoretic measure for balance assessment in comparative clinical studies
publisher	MDPI AG
series	Entropy
issn	1099-4300
publishDate	2020-02-01
description	Limitations of statistics currently used to assess balance in observation samples include their insensitivity to shape discrepancies and their dependence upon sample size. The Jensen−Shannon divergence (JSD) is an alternative approach to quantifying the lack of balance among treatment groups that does not have these limitations. The JSD is an information-theoretic statistic derived from relative entropy, with three specific advantages relative to using standardized difference scores. First, it is applicable to cases in which the covariate is categorical or continuous. Second, it generalizes to studies in which there are more than two exposure or treatment groups. Third, it is decomposable, allowing for the identification of specific covariate values, treatment groups or combinations thereof that are responsible for any observed imbalance.
topic	balance jensen–shannon divergence observational study relative entropy selection bias
url	https://www.mdpi.com/1099-4300/22/2/218
work_keys_str_mv	AT jarrodedalton aninformationtheoreticmeasureforbalanceassessmentincomparativeclinicalstudies AT williamabenish aninformationtheoreticmeasureforbalanceassessmentincomparativeclinicalstudies AT nikolasikrieger aninformationtheoreticmeasureforbalanceassessmentincomparativeclinicalstudies AT jarrodedalton informationtheoreticmeasureforbalanceassessmentincomparativeclinicalstudies AT williamabenish informationtheoreticmeasureforbalanceassessmentincomparativeclinicalstudies AT nikolasikrieger informationtheoreticmeasureforbalanceassessmentincomparativeclinicalstudies
_version_	1724868840875098112

An Information-Theoretic Measure for Balance Assessment in Comparative Clinical Studies

Similar Items