Bayesian evidence synthesis in case of multi-cohort datasets: An illustration by multi-informant differences in self-control.

The trend toward large-scale collaborative studies gives rise to the challenge of combining data from different sources efficiently. Here, we demonstrate how Bayesian evidence synthesis can be used to quantify and compare support for competing hypotheses and to aggregate this support over studies. We applied this method to study the ordering of multi-informant scores on the ASEBA Self Control Scale (ASCS), employing a multi-cohort design with data from four Dutch cohorts. Self-control reports were collected from mothers, fathers, teachers and children themselves. The available set of reporters differed between cohorts, so in each cohort varying components of the overarching hypotheses were evaluated. We found consistent support for the partial hypothesis that parents reported more self-control problems than teachers. Furthermore, the aggregated results indicate most support for the combined hypothesis that children report most problem behaviors, followed by their mothers and fathers, and that teachers report the fewest problems. However, there was considerable inconsistency across cohorts regarding the rank order of children's reports. This article illustrates Bayesian evidence synthesis as a method when some of the cohorts only have data to evaluate a partial hypothesis. With Bayesian evidence synthesis, these cohorts can still contribute to the aggregated results.

Testing sampling bias in estimates of adolescent social competence and behavioral control.

In 5 of the 6 large Dutch developmental cohorts investigated here, lower SES adolescents are underrepresented and higher SES adolescents overrepresented. With former studies clearly revealing differences between SES strata in adolescent social competence and behavioral control, this misrepresentation may contribute to an overestimation of normative adolescent competence. Using a raking procedure, we used national census statistics to weigh the cohorts to be more representative of the Dutch population. Contrary to our expectations, in all cohorts, little to no differences between SES strata were found in the two outcomes. Accordingly, no differences between weighted and unweighted mean scores were observed across all cohorts. Furthermore, no clear change in correlations between social competence and behavioral control was found. These findings are most probably explained by the fact that measures of SES in the samples were quite limited, and the low SES participants in the cohorts could not be considered as representative of the low SES groups in the general population. Developmental outcomes associated with SES may be affected by a raking procedure in other cohorts that have a sufficient number and sufficient variation of low SES adolescents.