Modelling latent trends from spatio-temporally grouped data using composite link mixed models

Epidemiological data are frequently recorded at coarse spatio-temporal resolutions. The aggregation process is done for several reasons: to protect confidential patients' information, to compare with other datasets at a coarser resolution than the original, or to summarize data in a compact manner. However, we lose detailed patterns that follow the original data, which can be of interest for researchers and public health officials. In this paper we propose the use of the penalized composite link model (Eilers, 2007), together with its mixed model representation, to estimate the underlying trend behind grouped data at a finer spatio-temporal resolution. Also, this model allows the incorporation of fine-scale population into the estimation procedure. We assume the underlying trend is smooth across space and time. The mixed model representation enables the use of sophisticated algorithms such as the SAP algorithm of Rodríguez- Álvarez et al. (2015) for fast estimation of the amount of smoothness. We illustrate our proposal with the analysis of data obtained during the largest outbreak of Q fever in the Netherlands.MTM2011-28285-C02-02, MTM2014-52184-