Research in epidemiology may be concerned with assessing risk factors for complex health issues described by several variables. Moreover, epidemiological data are usually organized in several blocks of variables, consisting of a block of variables to be explained and a large number of explanatory variables organized in meaningful blocks. Usual statistical procedures such as generalized linear models do not allow the explanation of a multivariate outcome, such as a complex disease described by several variables, with a single model. Moreover, it is not easy to take account of the organization of explanatory variables into blocks. Here we propose an innovative method in the multiblock modelling framework, called multiblock redundancy analysis, which is designed to handle most specificities of complex epidemiological data. Overall indices and graphical displays associated with different interpretation levels are proposed. The interest and relevance of multiblock redundancy analysis is illustrated using a dataset pertaining to veterinary epidemiology.

An innovative and well-adapted statistical method, called multiblock redundancy analysis, is proposed for a complex health-event analysis to account for the thematic block organization of variables. The outcome block contained the condemnation rates of 404 broiler chicken flocks, distinguishing infectious and traumatic condemnation categories. Explanatory variables were organized in blocks related to the different production stages (farm structure and routine husbandry practices; on-farm flock history and characteristics; catching, transport and lairage conditions; slaughterhouse and inspection features). The aim was to determine risk factors for both condemnation categories, and the relative impact of the different production stages on the whole condemnation rate. Results showed that significant factors were either specific to one condemnation category or related to both categories, and each of the explanatory blocks was involved in the explanation of infectious and traumatic condemnation rates. On-farm flock information explained 40% of the overall condemnation process whereas the other explanatory blocks had similar relative impacts.