ORI: A framework based on Order Restricted Inference to analyze data in chronobiology
In this talk we present a novel statistical framework to analyze periodic data in chronobiology.
This research is motivated by problems arising in the analysis of data obtained from oscillatory systems such as the circadian clock. We make several contributions to this field. First, we develop a methodology for describing rhythmicity using a circular signal plus error model. This mathematical formulation of rhythmicity is simple, easily interpretable and very flexible since it is not based on any mathematical function to describe the shape of the curve. Using this formulation, we develop a methodology to address the well-known rhythmicity detection problem. In many applications, times associated with each specimen is unknown, as in the case of samples from deceased subjects. In such cases, our proposed framework, based on the traveling salesman problem, provides a useful solution to estimate the true temporal order among the specimens along with determination of rhythmic components in the oscillatory system. Using simulations and real data, we demonstrate that our general methodology is substantially more efficient than the available methods.