Royal Statistical Society Highland Local Group Meeting announcement Wednesday 24th November at 1pm: venue: Fraser-Noble Lecture Theatre (3), King's College JOINT MEETING WITH ST ANDREWS UNIVERSITY speakers: Gillian Raab (Napier University), David Clayton (MRC, Cambridge), Denis Mollison (Heriot Watt University) programme: 1pm Gillian Raab (Napier University) Balance in Cluster Randomised Trials 2.15 pm coffee break 2.30 pm David Clayton (MRC Biostatistics Unit, Cambridge) Fitting complex random effect models with standard software using data augmentation: an application to a study of male and female fecundability. 3.45 pm coffee break 4pm Denis Mollison (Heriot Watt University) Modelling ecological and epidemic dynamics 5.30 end of meeting ------------------------------------------------------- Following the meeting a meal has been arranged in the private dining room in the Staff Refectory, King's College. Anyone wishing to join the speakers and committee for this meal are most welcome. Please contact myself by email if you intend to joint the party (by monday 22nd at latest) ABSTRACTS Gillian Raab title: Balance in cluster randomised trials Abstract: Intervention studies where the unit of analysis is a group of individuals, but inferences are required for individuals within the groups, are becoming increasing popular, especially for the evaluation of health policies. Although these studies may involve many individuals, the number of units of randomisation can be small. Thus they can be vulnerable to a poorly balanced randomisation. This talk will review the literature on the design of such cluster randomised studies and disuss the important role of balancing known features of the larger units in the design. David Clayton title: Fitting complex random effect models with standard software using data augmentation: an application to a study of male and female fecundability. Abstract: We discuss fitting of a complex random effect model using a standard statistical package (Stata) to carry out block-wise Gibbs sampling within a multi-processor computing environment. The application involves a dataset concerning artificial insemination by donor (AID). Success or failure at each or 12,100 menstrual cycles is modelled with a mixed model with random effects due to woman, conception attempt within woman, semen donor, donation within donor, and the treating physician. Given the availability of software within Stata to fit a model with single random effect, the full model can be fitted by an alternating imputation algorithm (Clayton & Rasbash, 1999) implemented with five copies of Stata running on separate processors and communicating via disk files. Denis Mollison title: Modelling ecological and epidemic dynamics Abstract: Questions of invasion, growth, equilibrium and persistence are of great importance in population modelling. The talk will review and compare different types of models, particularly stochastic and deterministic, with both ecological and epidemic illustrations. web page:http://www.maths.abdn.ac.uk/maths/department/rss/highlands.html _______________________________________________________ Dr Andrew B. Lawson Department of Mathematical Sciences University of Aberdeen Aberdeen AB24 3UE UK phone: 44-1224-272615 (voice mail) fax: 44-1224-272607 email: [log in to unmask] ________________________________________________________ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%