pone.0169901.g001.tif (2.64 MB)
Download file

Conceptual illustration of the model.

Download (2.64 MB)
posted on 2017-01-11, 17:32 authored by Andrea Cuttone, Per Bækgaard, Vedran Sekara, Håkan Jonsson, Jakob Eg Larsen, Sune Lehmann

We assume that for each day the event counts follow two different Poisson distributions: one for sleep periods (rate λsleep) and one for awake periods (rate λawake). Furthermore we assume that two switchpoints tsleep and tawake determine the rate (i.e. the Poisson distribution) that generates the events.