models can be binomial, multinomial, tree (nested) logit model or, in version 4EC, mixed logit. Tree models can be specified with many branches (up to 250 nodes in 3.2 and unlimited number in 4) and unlimited 'levels';

revealed preference or stated preference, disaggregate or aggregate data can be used; choice, ranking or proportional split data can be employed; ALOGIT is compatible with HCG Software's MINT and SPEED interview and stated preference software and EXSYS presentation program;

input data can be manipulated and transformed freely to allow the user freedom in finding the required explanation of behaviour; extensive testing of input data to reveal modelling problems; simple controls, yet giving access when required to full sophistication;

all coefficients are estimated simultaneously (up to 125 coefficients in 3.2, unlimited number in version 4) to get correct models (i.e. 'full information' estimates) and to simplify the analysis;

coefficient estimates, standard errors, correctly calculated elasticities, consumer surplus measures and several detailed tests are all standard; informative, clearly labelled, well-laid-out output, suitable for immediate incorporation in reports;

non-linear utility functions allow attraction variables to be included correctly;

'composite' alternatives can be indicated as chosen;

enhanced forecasting features

thoroughly tested in projects by HCG, RAND Europe and others over many years.

fully supported and maintained to keep abreast of modern computer and modelling techniques; ALOGIT is very fast in operation; ALOGIT can be specifically installed for your PC system