Spatial microsimulation models for rail travel: a West Yorkshire case study

Consumer data are potentially rich in context, exposing more predictors of behaviour but inadvertent missing values skew these datasets and compromise the validity of the thesis. The distinct process which causes the missing values is paramount in plugging these gaps, and a principled remedy put forward by the statistics community is to integrate additional data variables that explain the difference between the missing and observed values. Our current research applies the above hypothesis to big consumer data revealed from the UK railways, to create a requisite integrated big dataset suitable for subsequent mobility analysis of local finer scale phenomena. Ultimately the aim is to investigate case studies like rail-heading (whereby passengers travel further to access a rail service when there are commensurate closer services). Such studies aid initiatives identifying the socio-economic, demographic, urban morphology and network endogenous variables which govern passenger choice behaviour.