ESRC Social Research Methods Festival St Catherine’s College, Oxford, 1 - 3 July 2004 On Thursday 1 July five projects funded by the ESRC’s flagship Method’s Programme will be reporting their research on modelling complex processes. These include the importance of modelling error variance and covariance structures when examining (possibly) reciprocal effects (Peter Smith, Southampton); addressing the problem of endogeneity in estimating area effects (Simon Burgess, Bristol); multilevel multiprocess models for partnership and childbearing event histories (Fiona Steele, Institute of Education); methods for studying families and family effects: the systematic assessment of research designs and data analytic strategies (Jon Rasbash, Institute of Education and Tom O’Connor, Institute of Psychiatry); and multilevel models with missing data (James Carpenter, LSHTM). Other sessions include new directions in multidimensional analysis and methods of analysis for international comparisons. A number of debates will be taking place, for example on the role of trials in policy assessment; ‘Causality’ with exchanges between statisticians, economists, sociologists and also policy makers. All sessions have plenty of time for questions and discussion. More information on the Research Methods Programme, directed by Angela Dale, can be found at: www.ccsr.ac.uk/methods