Search

Background: When study data are clustered, standard regression analysis is considered inappropriate and analytical techniques for clustered data need to be used. For prediction research in which the interest of predictor effects is on the patient level, random effect regression models are probably preferred over standard regression analysis. It is well known that the random effect parameter estimates and the standard logistic regression parameter estimates are different. Here, we compared random effect and standard logistic regression models for their ability to provide accurate predictions. Methods: Using an empirical study on 1642 surgical patients at risk of postoperative nausea and vomiting, who were treated by one of 19 anesthesiologists (clusters), we developed prognostic models either with standard or random intercept logistic regression. External validity of these models was assessed in new patients from other anesthesiologists. We supported our results with simulation studies using intra-class correlation coefficients (ICC) of 5%, 15%, or 30%. Standard performance measures and measures adapted for the clustered data structure were estimated. Results: The model developed with random effect analysis showed better discrimination than the standard approach, if the cluster effects were used for risk prediction (standard c-index of 0.69 versus 0.66). In the external validation set, both models showed similar discrimination (standard c-index 0.68 versus 0.67). The simulation study confirmed these results. For datasets with a high ICC (⩾15%), model calibration was only adequate in external subjects, if the used performance measure assumed the same data structure as the model development method: standard calibration measures showed good calibration for the standard developed model, calibration measures adapting the clustered data structure showed good calibration for the prediction model with random intercept. Conclusion: The models with random intercept discriminate better than the standard model only if the cluster effect is used for predictions. The prediction model with random intercept had good calibration within clusters. [ABSTRACT FROM AUTHOR]

Background: Within longitudinal epidemiological research, 'count' outcome variables with an excess of zeros frequently occur. Although these outcomes are frequently analysed with a linear mixed model, or a Poisson mixed model, a two-part mixed model would be better in analysing outcome variables with an excess of zeros. Therefore, objective of this paper was to introduce the relatively 'new' method of two-part joint regression modelling in longitudinal data analysis for outcome variables with an excess of zeros, and to compare the performance of this method to current approaches. Methods: Within an observational longitudinal dataset, we compared three techniques; two 'standard' approaches (a linear mixed model, and a Poisson mixed model), and a two-part joint mixed model (a binomial/Poisson mixed distribution model), including random intercepts and random slopes. Model fit indicators, and differences between predicted and observed values were used for comparisons. The analyses were performed with STATA using the GLLAMM procedure. Results: Regarding the random intercept models, the two-part joint mixed model (binomial/Poisson) performed best. Adding random slopes for time to the models changed the sign of the regression coefficient for both the Poisson mixed model and the two-part joint mixed model (binomial/Poisson) and resulted into a much better fit. Conclusion: This paper showed that a two-part joint mixed model is a more appropriate method to analyse longitudinal data with an excess of zeros compared to a linear mixed model and a Poisson mixed model. However, in a model with random slopes for time a Poisson mixed model also performed remarkably well. [ABSTRACT FROM AUTHOR]

Background: In population studies, body mass index (BMI) is generally calculated from self-reported body weight and height. The self-report of these anthropometrics is known to be biased, resulting in a misclassification of BMI status. The aim of our study is to evaluate the accuracy of self-reported weight, height and waist circumference among a Dutch overweight (Body Mass Index [BMI] > or = 25 kg/m2) working population, and to determine to what extent the accuracy was moderated by sex, age, BMI, socio-economic status (SES) and health-related factors., Methods: Both measured and self-reported body weight and body height were collected in 1298 healthy overweight employees (66.6% male; mean age 43.9 +/- 8.6 years; mean BMI 29.5 +/- 3.4 kg/m2), taking part in the ALIFE@Work project. Measured and self-reported waist circumferences (WC) were available for a sub-group of 250 overweight subjects (70.4% male; mean age 44.1 +/- 9.2 years; mean BMI 29.6 +/- 3.0 kg/m2). Intra Class Correlation (ICC), Cohen's kappa and Bland Altman plots were used for reliability analyses, while linear regression analyses were performed to assess the factors that were (independently) associated with the reliability., Results: Body weight was significantly (p < 0.001) under-reported on average by 1.4 kg and height significantly (p < 0.001) over-reported by 0.7 cm. Consequently, BMI was significantly (p < 0.001) under-reported by 0.7 kg/m2. WC was significantly (p < 0.001) over-reported by 1.1 cm. Although the self-reporting of anthropometrics was biased, ICC's showed high concordance between measured and self-reported values. Also, substantial agreement existed between the prevalences of BMI status and increased WC based on measured and self-reported data. The under-reporting of BMI and body weight was significantly (p < 0.05) affected by measured weight, height, SES and smoking status, and the over-reporting of WC by age, sex and measured WC., Conclusion: Results suggest that self-reported BMI and WC are satisfactorily accurate for the assessment of the prevalence of overweight/obesity and increased WC in a middle-aged overweight working population. As the accuracy of self-reported anthropometrics is affected by measured weight, height, WC, smoking status and/or SES, results for these subgroups should be interpreted with caution. Due to the large power of our study, the clinical significance of our statistical significant findings may be limited., Trial Registration: ISRCTN04265725.