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
Digitalization is the core component of future development in the 4.0 industrial era. It represents a powerful mechanism for enhancing the sustainable competitiveness of economies worldwide. Diverse triggering effects shape future digitalization trends. Thus, the main research goal in this study is to use sustainable competitiveness pillars (such as social, economic, environmental and energy) to evaluate international digitalization development. The proposed empirical model generates comprehensive knowledge of the sustainable competitiveness-digitalization nexus. For that purpose, a nonlinear regression has been applied on gathered annual data that consist of 33 European countries, ranging from 2010 to 2016. The dataset has been deployed using Bernoulli’s binominal distribution to derive training and testing samples and the entire analysis has been adjusted in that context. The empirical findings of artificial neural networks (ANN) suggest strong effects of the economic and energy use indicators on the digitalization progress. Nonlinear regression and ANN model summary report valuable results with a high degree of coefficient of determination (R2>0.9 for all models). Research findings state that the digitalization process is multidimensional and cannot be evaluated as an isolated phenomenon without incorporating other relevant factors that emerge in the environment. Indicators report the consumption of electrical energy in industry and households and GDP per capita to achieve the strongest effect.
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.
