Methodology of a multi-site reliability study - EPSILON Study 3

Background The European Psychiatric Services: Inputs Linked to Outcome Doma ins and Needs (EPSILON) Study aims to produce standardised versions in five European languages of instruments measuring needs for care, family or care giving burden, satisfaction with services, quality of life. and sociodemogr aphic and service receipt. Aims To describe background, rationale and design of the reliability study, focusing on reliable instruments, reliability testing theory, a general re liability testing procedure and sample size requirements. Method A strict protocol was developed. consisting of definitions of the sp ecific reliability measures used, the statistical methods used to assess th ese reliability coefficients, the development of statistical programmes to make intercentre reliability comparisons, criteria for good reliability. an d a general format for the reliability analysis. Conclusion The reliability analyses are based on classical test theory. Rel iability measures used are Cronbach's alpha, Cohen's IC and the intraclass correlation coefficient. Intersite comparisons were extended with a compari son of the standard error of measurement. Criteria for good reliability may need to be adapted for this type of study The consequences of low reliabil ity, and reliability differing between sites, must be considered before poo ling data. Declaration of interest No conflict of interest. Funding detailed in Acknow ledgements.