Statistical methods used for the study of correlation and/or linkage between HLA and diseases susceptibility will be different according to the aim of the study. In case of a search of an association between disease character and HLA markers in unrelated populations, the methodology used will be based upon chi square and Relative Risk. In case of linkage study: multiplex families with 2 or more patients bring the most informative data. In all cases, a particular attention must be paid to criteria used for selection of patients and controls, and for studies of linkage to the hypothesis concerning mode of inheritance and penetrance required by the model chosen.