Home About us Contact
|
Home About us Contact | ||
|
|
||
Intracluster Correlation Coefficient (intracluster + correlation_coefficient)
Selected AbstractsApplication of an adjusted ,2 statistic to site-specific data in observational dental studiesJOURNAL OF CLINICAL PERIODONTOLOGY, Issue 1 2002Chul Ahn Abstract Background: When a binary response is observed on teeth from each subject belonging to 2 or more exposure groups, application of the usual Pearson ,2 tests is invalid, since such responses within the same subject are not independent. Consequently, special statistical methods are needed to control for the correlation among teeth (sites) within the same subject. A simple adjustment to the Pearson ,2 statistic has been proposed for comparing proportions in site-specific data. However, the required assumptions for this statistic have not yet been thoroughly addressed. These assumptions are guaranteed to hold in experimental comparisons, but may be violated in some observational studies. Method: We investigate the conditions under which the adjusted ,2 statistic is valid and examine the performance of the adjusted ,2 statistic when these conditions are violated. Results: Our simulation study shows that the adjusted ,2 statistic generally produces good empirical type I errors under the assumption of a common intracluster correlation coefficient. Even if the intracluster correlations are different, the adjusted statistic performs well when the groups have equal numbers of clusters (subjects). Conclusion: The discussion is illustrated using an observational study of caries on the roots of teeth. Zusammenfassung Hintergründe: Wenn eine binäre Antwort auf Zähne von jedem Subjekt, das zu 2 oder mehreren experimentellen Gruppen gehört, benutzt wird, ist die Anwendung des gewöhnlich genutzten Pearson ,2 Testes nicht zulässig, da solche Antworten innerhalb des selben Subjektes nicht unabhängig sind. In der Konsequent werden spezielle statistische Methoden gebraucht, um die Korrelation unter den Zähnen (Flächen) innerhalb desgleichen Subjektes zu kontrollieren. Eine simple Adjustierung zu der Pearson ,2 Statistik wurde vorgeschlagen, um die Verhältnisse der flächenspezifischen Daten zu vergleichen. Jedoch wurde sich der notwendigen Anwendung für diese Statistik noch nicht ausführlich gewidmet. Diese Anwendungen sind garantiert bei experimentellen Vergleichen anzuwenden, aber mögen in einigen beobachteten Studien verletzt werden. Methoden: Wir untersuchten die Bedingungen unter welchen der adjustierte ,2 Test richtig ist und prüften die Leistung des adjustierten ,2 Testes, wenn diese Bedingungen verletzt werden. Ergebnisse: Unsere Simulationsstudie zeigt, dass die adjustierte ,2 Statistik im Allgemeinen gute empirische Irrtümer vom Typ I erbringt unter der Anwendung eines gewöhnlichen Intracluster Korrelationskoeffizienten. Auche wenn die Intracluster-Korrelationen unterschiedlich sind, ist die adjustierte Statistik gut zu nutzen, wenn die Gruppen gleiche Nummern von Clustern haben (Subjekte). Schlußfolgerungen: Die Diskussion wird illustriert unter Nutzung einer beobachteten Studie von Wurzelkaries. Résumé Origine: Lorsqu'une réponse binaire est observée sur les dents de chaque sujet appartenant à 2 groupes ou plus, l'application du test habituel ,2 de Pearson n'est pas valable puisque de telles réponses pour le même sujet sont indépendante. En conséquence, des méthodes statistiques spéciales sont nécessaires pour contrôler les corrélation entre les dents (sites) pour le même sujet. Un simple ajustement de la statistique ,2 de Pearson a été proposée pour comparer les proportions pour les données spécifiques de sites. Cependant, les hypothèses requises pour cette statistique n'ont pas encore été consciencieusement émises. Ces hypothèses sont certifiées être valable pour les comparaisons experimentales, mais peuvent ne pas être respectées dans quelques études observationnelles. Méthode: Nous recherchons les conditions pour lesquelles la statistique ,2 ajustée est valable et examinons sa performance lorsque ces conditions ne sont pas respectées. Résultats: Notre étude simulée montre que la statistique ,2 ajustée produit généralement de bonnes érreurs empiriques de type 1 dans l'hypothèse d'un coéfficient de corrélation commun intra-groupe. Même si les corrélations intragroupes sont différentes, la statistique ,2 ajustée s'exécute bien quand les ensembles ont des nombres égaux de groupes (sujets). Conclusion: La discussion est illustrée par une étude observationnelle des caries radiculaires. [source] Imputation Strategies for Missing Continuous Outcomes in Cluster Randomized TrialsBIOMETRICAL JOURNAL, Issue 3 2008Monica Taljaard Abstract In cluster randomized trials, intact social units such as schools, worksites or medical practices , rather than individuals themselves , are randomly allocated to intervention and control conditions, while the outcomes of interest are then observed on individuals within each cluster. Such trials are becoming increasingly common in the fields of health promotion and health services research. Attrition is a common occurrence in randomized trials, and a standard approach for dealing with the resulting missing values is imputation. We consider imputation strategies for missing continuous outcomes, focusing on trials with a completely randomized design in which fixed cohorts from each cluster are enrolled prior to random assignment. We compare five different imputation strategies with respect to Type I and Type II error rates of the adjusted two-sample t -test for the intervention effect. Cluster mean imputation is compared with multiple imputation, using either within-cluster data or data pooled across clusters in each intervention group. In the case of pooling across clusters, we distinguish between standard multiple imputation procedures which do not account for intracluster correlation and a specialized procedure which does account for intracluster correlation but is not yet available in standard statistical software packages. A simulation study is used to evaluate the influence of cluster size, number of clusters, degree of intracluster correlation, and variability among cluster follow-up rates. We show that cluster mean imputation yields valid inferences and given its simplicity, may be an attractive option in some large community intervention trials which are subject to individual-level attrition only; however, it may yield less powerful inferences than alternative procedures which pool across clusters especially when the cluster sizes are small and cluster follow-up rates are highly variable. When pooling across clusters, the imputation procedure should generally take intracluster correlation into account to obtain valid inferences; however, as long as the intracluster correlation coefficient is small, we show that standard multiple imputation procedures may yield acceptable type I error rates; moreover, these procedures may yield more powerful inferences than a specialized procedure, especially when the number of available clusters is small. Within-cluster multiple imputation is shown to be the least powerful among the procedures considered. (© 2008 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim) [source] The impact of psoriasis guidelines on appropriateness of referral from primary to secondary care: a randomized controlled trialBRITISH JOURNAL OF DERMATOLOGY, Issue 2 2006C.E.M. Griffiths Summary Background, Most patients with psoriasis have limited disease which can be managed effectively in primary care. There is a marked variation in the frequency of referrals between practices reflecting, in part, inadequate training of general practitioners (GPs) in the management of psoriasis. Objectives, To assess the effectiveness of guidelines and training sessions on the management of psoriasis in reducing inappropriate referrals from primary care. Methods, Patients aged 18 years or over with psoriasis were eligible for the cluster-randomized, randomized controlled trial if they were referred by their GP between 9 September 2002 and 31 December 2003 to one of four hospital dermatology departments in Greater Manchester, North-West England. All GPs from 165 health centres were invited to a lecture by a local dermatologist on the diagnosis and management of psoriasis. Health centres in the intervention arm received guidelines on the management of psoriasis in primary care, developed by local dermatologists, supplemented by the offer of a practice-based nurse-led training session; those in the control arm received neither guidelines nor training sessions. Results, Eighty-two health centres were randomized to the intervention arm and 83 to the control arm. Outcome data were available for 188 of the 196 eligible patients referred during the study period. Patients in the intervention arm were significantly more likely to be appropriately referred in comparison with patients in the control arm [difference = 19·1%; odds ratio (OR) 2·47; 95% confidence interval (CI) 1·31,4·68; intracluster correlation coefficient (ICC) = 0]. Only 25 (30%) health centres in the intervention arm took up the offer of training sessions. There was no significant difference in outcome between health centres in the intervention arm that received a training session and those that did not (OR 1·28, 95% CI 0·50,3·29, ICC = 0). Conclusions, Dissemination of guidelines on the management of psoriasis in primary care can significantly enhance the appropriateness of referral of patients to secondary care. [source] Modelling Multivariate Outcomes in Hierarchical Data, with Application to Cluster Randomised TrialsBIOMETRICAL JOURNAL, Issue 3 2006Rebecca M. Turner Abstract In the cluster randomised study design, the data collected have a hierarchical structure and often include multivariate outcomes. We present a flexible modelling strategy that permits several normally distributed outcomes to be analysed simultaneously, in which intervention effects as well as individual-level and cluster-level between-outcome correlations are estimated. This is implemented in a Bayesian framework which has several advantages over a classical approach, for example in providing credible intervals for functions of model parameters and in allowing informative priors for the intracluster correlation coefficients. In order to declare such informative prior distributions, and fit models in which the between-outcome covariance matrices are constrained, priors on parameters within the covariance matrices are required. Careful specification is necessary however, in order to maintain non-negative definiteness and symmetry between the different outcomes. We propose a novel solution in the case of three multivariate outcomes, and present a modified existing approach and novel alternative for four or more outcomes. The methods are applied to an example of a cluster randomised trial in the prevention of coronary heart disease. The modelling strategy presented would also be useful in other situations involving hierarchical multivariate outcomes. (© 2006 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim) [source] | ||||||||||