Ling Ma ColloquiumThursday, August 31, 2017 - 2:45pm
Statistics Department Colloquium
Where: LeConte College, Room 210
Speaker: Ling Ma
In longitudinal studies, it is often of interest to investigate how the functional feature of a marker’s measurement process is associated with the event time of interest. We make use of B-splines to smoothly approximate the infinite dimensional functional data and propose a joint model of the longitudinal functional feature and the time to event. The proposed approach also allows for prediction of survival probabilities for future subjects based on their available longitudinal measurements and a fitted joint model. We illustrate our proposals on a prospective pregnancy study, namely Oxford Conception Study, where hormonal measurements of luteinizing hormone which is an important biomarker of ovulation is available. A joint modeling approach using functional analytic approach and discrete survival modeling was used to assess whether the functional feature of hormonal measurements, such as the curvature of the hormonal profile is associated with time to pregnancy.