Investigating Determinants of Multiple Sclerosis in Longitunal Studies: A Bayesian Approach

Modelling data from Multiple Sclerosis longitudinal studiesis a challenging topic since the phenotype of interest is typically ordinal;time intervals between two consecutive measurements are nonconstantand they can vary among individuals. Due to these unobservablesources of heterogeneity statistical models for analysis of Multiple Sclerosisseverity evolve as a difficult feature. A few proposals have beenprovided in the biostatistical literature (Heijtan (1991); Albert, (1994)) toaddress the issue of investigating Multiple Sclerosis course. In this paperBayesian P-Splines (Brezger and Lang, (2006); Fahrmeir and Lang(2001)) are indicated as an appropriate tool since they account for nonlinearsmooth effects of covariates on the change in Multiple Sclerosisdisability. By means of Bayesian P-Spline model we investigate boththe randomness affecting Multiple Sclerosis data as well as the ordinalnature of the response variable