EVALUATION OF LOGIT AND PROBIT MODELS IN MODE-CHOICE SITUATION
Two statistical tools that are suitable for analyzing modal split situation are logit models and probit models. From an analytical point of view, logit is superior; but, for theoretic reliability, probit is the better model. The aim of this paper is to compare and assess the predictive ability of logit and probit models when employed in mode choice context. Two transit modes operating in different cities of the Saudi Kingdom were analyzed. The attributes of the transport system, traveler, and trip were considered, as they represent the major components of the utility function. Including transport system attributes was termed as a partially-specified model, while submitting traveler and trip attributes was denoted as a full-specified model. The assessment stage was based on various criteria, such as inconsistency and significance of model's coefficients, goodness-of-fit measure, outlier analysis, and market segment test. Use of the full-specified model is recommended because of its ability to duplicate the overall process of mode choice more accurately. The author discourages the calibration of complicated models, such as probit, when analyzing the situation of a binary mode choice because logit model provides more accurate predictions.
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/oclc/8674831
-
Corporate Authors:
American Society of Civil Engineers
345 East 47th Street
New York, NY United States 10017-2398 -
Authors:
- Ghareib, A H
- Publication Date: 1996-7
Language
- English
Media Info
- Features: Appendices; References; Tables;
- Pagination: p. 282-290
-
Serial:
- Journal of Transportation Engineering
- Volume: 122
- Issue Number: 4
- Publisher: American Society of Civil Engineers
- ISSN: 0733-947X
- Serial URL: https://ascelibrary.org/journal/jtepbs
Subject/Index Terms
- TRT Terms: Accuracy; Alternatives analysis; Analysis; Evaluation; Logits; Mode choice; Probits; Transportation modes
- Old TRIS Terms: Attributes; Predictive ability
- Subject Areas: Highways; Planning and Forecasting; Public Transportation; I72: Traffic and Transport Planning;
Filing Info
- Accession Number: 00726104
- Record Type: Publication
- Files: TRIS, ATRI
- Created Date: Sep 25 1996 12:00AM