THE ROYAL STATISTICAL SOCIETY ================================= TIMSAC (Time Series and Applications) Study Group Meeting --------------------------------------------------------------- Thursday 11 March 1999, 4:00 pm ========================================== The Royal Statistical Society, 12 Errol Street, London EC1 (Nearest Underground stations: Barbican, Moorgate) DENISE OSBORN (University of Manchester) " Modelling business cycle movements in the UK economy" ALLAN TIMMERMANN (London School of Economics) "Dangers of data-driven inference: The case of calendar effects in stock returns" A L L A R E W E L C O M E ! SUMMARIES DENISE OSBORN The talk relates to the business cycle in the sense that recessions have distinctive characteristics compared with expansions. Economists have adopted and developed nonlinear time series models of the "regime switching" type to capture these characteristics. We apply such models to UK macroeconomic variables and examine their performance during the recession of the early 1990s. Tea break at 4:45 p.m. ALLAN TIMMERMAN Economics and finance are non-experimental sciences which cannot generate new data sets. The common practice of using the same data set to test hypotheses introduces data-snooping biases that invalidate assumptions underlying statistical inference. The talk discusses a bootstrap procedure that controls for data-snooping biases and overturns conventional wisdom about the existence of calendar effects in stock returns. Information on TIMSAC can be found on: http://www.zoo.cam.ac.uk/timsac/timsac.htm or contact: [log in to unmask], (Barbel Finkenstadt, Department of Zoology, University of Cambridge, Downing Street, Cambridge CB2 3EJ, tel/fax ++44 (0)1223 336644) %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%