Curvaceous model of recovery from depression

Modeling the Recovery from Depressive Illness by an Exponential Model with Mixed Effects

“…Thereby, they chose an arbitrary value for the score after complete recovery. This approach was criticized by Boyer [3] and by Livingston and Clark [4] because of the data-independent choice of a model parameter and because of modeling the mean values and not individual recovery curves. In the approach presented in this paper, scores after complete recovery are estimated from the data and individual recovery curves are fitted by random effects associated with the patients.…”

“…First, there is no difference between the models in (3) and (4) because (4) follows from (3) by setting b i1 * = b i1 -b i3 . Concerning the interpretation of the random effects, however, there are differences between these two models.…”

“…The approach of Priest et al [2] was criticized by Boyer [3], and Livingston and Clark [4]. Especially the arbitrary choice of the score after complete recovery (␤ 3 ) was found to be insufficient.…”

Delay in onset of action of antidepressants

“…In 1996 my colleagues and I published evidence that the fall in scores on the Hamilton Rating Scale for Depression followed an exponential decay curve with a correlation coefficient of 0.99 (Priest et al , 1996; Livingston & Clark, 1997). This observation corresponds with Mitchell's remarks on the steep fall in scores in the first 2 weeks.…”