BackgroundConfounding bias is a common concern in epidemiological research. Its presence is often determined by comparing exposure effects between univariable- and multivariable regression models, using an arbitrary threshold of a 10% difference to indicate confounding bias. However, many clinical researchers are not aware that the use of this change-in-estimate criterion may lead to wrong conclusions when applied to logistic regression coefficients. This is due to a statistical phenomenon called noncollapsibility, which manifests itself in logistic regression models. This paper aims to clarify the role of noncollapsibility in logistic regression and to provide guidance in determining the presence of confounding bias.MethodsA Monte Carlo simulation study was designed to uncover patterns of confounding bias and noncollapsibility effects in logistic regression. An empirical data example was used to illustrate the inability of the change-in-estimate criterion to distinguish confounding bias from noncollapsibility effects.ResultsThe simulation study showed that, depending on the sign and magnitude of the confounding bias and the noncollapsibility effect, the difference between the effect estimates from univariable- and multivariable regression models may underestimate or overestimate the magnitude of the confounding bias. Because of the noncollapsibility effect, multivariable regression analysis and inverse probability weighting provided different but valid estimates of the confounder-adjusted exposure effect. In our data example, confounding bias was underestimated by the change in estimate due to the presence of a noncollapsibility effect.ConclusionIn logistic regression, the difference between the univariable- and multivariable effect estimate might not only reflect confounding bias but also a noncollapsibility effect. Ideally, the set of confounders is determined at the study design phase and based on subject matter knowledge. To quantify confounding bias, one could compare the unadjusted exposure effect estimate and the estimate from an inverse probability weighted model.
MULTIFILE
Objective: To explore predictors of dropout of patients with chronic musculoskeletal pain from an interdisciplinary chronic pain management programme, and to develop and validate a multivariable prediction model, based on the Extended Common- Sense Model of Self-Regulation (E-CSM). Methods: In this prospective cohort study consecutive patients with chronic pain were recruited and followed up (July 2013 to May 2015). Possible associations between predictors and dropout were explored by univariate logistic regression analyses. Subsequently, multiple logistic regression analyses were executed to determine the model that best predicted dropout. Results: Of 188 patients who initiated treatment, 35 (19%) were classified as dropouts. The mean age of the dropout group was 47.9 years (standard deviation 9.9). Based on the univariate logistic regression analyses 7 predictors of the 18 potential predictors for dropout were eligible for entry into the multiple logistic regression analyses. Finally, only pain catastrophizing was identified as a significant predictor. Conclusion: Patients with chronic pain who catastrophize were more prone to dropout from this chronic pain management programme. However, due to the exploratory nature of this study no firm conclusions can be drawn about the predictive value of the E-CSM of Self-Regulation for dropout.
DOCUMENT
Thirty to sixty per cent of older patients experience functional decline after hospitalisation, associated with an increase in dependence, readmission, nursing home placement and mortality. First step in prevention is the identification of patients at risk. The objective of this study is to develop and validate a prediction model to assess the risk of functional decline in older hospitalised patients.
DOCUMENT
