Psychopharmacol Bull
-
Psychopharmacol Bull · Jan 1991
ReviewA note on randomization and selection bias in maintenance therapy clinical trials.
In this article we demonstrate that even in randomized controlled clinical trials, unobserved confounding variables can bias the outcome of a study. For the case of a two-phase maintenance therapy trial where patients who respond to treatment during the acute phase are then randomized to a maintenance therapy, we show explicitly the role that confounding may play in biasing the interpretation of the results of such a trial. We suggest an alternative design to deal with the problem of a selection effect for treatment responders in the acute phase of the trial by randomizing patients at the outset of the study to both an acute and maintenance therapy.
-
Psychopharmacol Bull · Jan 1991
Randomized Controlled Trial Clinical TrialPredictors of side effects associated with lithium administration in children.
Data were pooled from three controlled and double-blind studies of lithium carbonate involving a total of 48 hospitalized children, and secondary data analyses were conducted. The objective was to assess whether there is a relationship between a child's chronological age and side effects associated with lithium administration. ⋯ For the entire sample of 48 children, the effect of age on side effects was statistically significant (p = .057); younger children had more side effects than older children. This relationship continued to hold after adjustment for weight, serum lithium levels, optimal dose, and duration of optimal dose.