Premium
Strengthening the case for disease management effectiveness: un‐hiding the hidden bias
Author(s) -
Linden Ariel,
Adams John L.,
Roberts Nancy
Publication year - 2006
Publication title -
journal of evaluation in clinical practice
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.737
H-Index - 73
eISSN - 1365-2753
pISSN - 1356-1294
DOI - 10.1111/j.1365-2753.2005.00612.x
Subject(s) - observational study , covariate , randomized controlled trial , randomization , medicine , intervention (counseling) , case management , econometrics , nursing , mathematics , surgery
As is the case with most health care program evaluations, disease management (DM) programs typically follow an observational study design, indicating that randomization to treatment or control was not performed. The foremost limitation of observational studies, compared to randomized studies, is that the only biases that can be controlled for are those associated with observed variables. Hidden bias refers to all those unobserved covariates that may distort the conclusions of the study. This paper introduces a sensitivity analysis that is used to determine the magnitude of hidden bias necessary to alter the conclusion that a DM program intervention was indeed effective.