Access Restriction

Author Mamun, Shahid ♦ Sabbir, Ahsan
Source CiteSeerX
Content type Text
File Format PDF
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Spatial Transferability ♦ Mode Choice Model ♦ San Francisco Bay Area ♦ Previous Study ♦ Sample Share ♦ Dfw Application Dataset ♦ Modal Share ♦ Bat Application Dataset ♦ Multinomial Logit Model ♦ Abstract Many Study ♦ Travel Cost ♦ Main Focus ♦ Application Dataset ♦ Regional Datasets ♦ Temporal Transferability ♦ Different Region ♦ Way Model ♦ Whole Data ♦ Dallas-fort Worth ♦ Explanatory Variable ♦ Important Variable ♦ Identical Data Set
Abstract Abstract—Many studies have been performed in the field of transferability of mode choice model. Both temporal and spatial transferability were covered in the previous studies although temporal transferability got main focus in this respect. Most of the research on spatial transferability was performed on identical data sets. This research examines the effect of omission of one of the most important variables (travel cost) in spatial transferability. Multinomial logit models are used for building mode choice models. Two sets of data from two different regions are used: one from Dallas-Fort Worth (DFW) and another from the San Francisco Bay Area (BATS). Each of the datasets is randomly divided into two samples: estimated dataset (90 % of the whole data) and application dataset (10 % of the sample). Model estimated from BATS’s estimated dataset is applied to BATS’s application dataset as well as DFW’s estimated dataset. In the same way model estimated from DFW’s estimated dataset is applied to DFW’s application dataset as well as BATS’s estimated dataset. No adjustment is done for transferring the models. The study finds that the parameters of explanatory variable of the models estimated from two regional datasets are similar in terms of sign and magnitude. Modal shares predicted by models are almost same as sample shares within the region and outside the region.
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study