Share on facebook
Save on delicious
RSS Feed
Statistical Analyses
CQeSS continually evaluates available statistical software and is also increasing the range of models that can be estimated with Lancaster's SABRE software. SABRE software has been specifically designed for the statistical analysis of multi-process random effect response data. These responses can take the form of binary, ordinal, count and linear recurrent events. The response sequences can be of different types. Such multi-process data is common in many research areas, e.g. the analysis of work and life histories (voting, trade union membership, economic activity and migration, absenteeism). SABRE has been used intensively on many longitudinal datasets surveys either with recurrent information collected over time or with a clustered sampling scheme, details of examples of the use of SABRE can be found at http://sabre.lancs.ac.uk/examples.html
Support for parallel processing, introduced in version 4.0 can dramatically cut run times by many orders of magnitude. An illustration of the performance of SABRE, using an increasing number of processors for the estimation of a model is presented below. The tests were performed on a 63 variable analyses of 3.7 x 10 6 observations (2Gb file). The 2 left most columns are the timings for STATA and Gllamm achieved on the same computers and the same dataset.
Currently we are working towards adding both multilevel and fixed effects models to SABRE.
SABRE is open source, the software and manuals can be found at the SABRE website.