THE N-DIMENSIONAL LOGIT MODEL: DEVELOPMENT AND APPLICATION

Abstract

THE MODEL IS BASED ON THE ASSUMPTION THAT THE RATIO OF A SMALL CHANGE IN MODAL SPLIT OF A GIVEN MODE TO THAT OF A GIVEN TRANSPORTATION VARIABLE IS PROPORTIONAL TO THE MODAL SPLIT OF THIS MODE AND TO A LINEAR FUNCTION OF THE MODAL SPLIT OF ALL MODES. IN CONJUNCTION WITH THE MATHEMATICAL DEFINITION RELATING TO MODAL SPLIT, THESE ASSUMPTIONS LEAD TO A SYSTEM OF DIFFERENTIAL EQUATIONS DEFINING MODAL-MARKET SHARES AS FUNCTIONS OF THE TRANSPORTATION ATTRIBUTES. THIS FORMULATION DOES NOT REQUIRE THAT THE SAME SET OF VARIABLES BE USED TO DEFINE THE TRANSPORTATION ATTRIBUTES OF EACH OF THE MODES. THE MODEL WAS APPLIED TO PREDICT THE MARKET SHARES OF 4 MODES-PRIVATE AUTOMOBILE, RENTAL CAR, TAXI, AND LIMOUSINE-USED FOR ACCESS (OR EGRESS) TO (OR FROM) AIRPORTS IN THE BALTIMORE-WASHINGTON AREA. CALIBRATION RESULTS INDICATE THAT THE COEFFICIENTS ESTIMATED HAVE THE EXPECTED SIGNS AND RELATIVE MAGNITUDES AS WELL AS LOW STANDARD ERRORS OF ESTIMATE. TESTING INDICATES THAT THE MODEL DISPLAYS THE APPROPRIATE SENSITIVITIES AND ADEQUATELY REPRODUCES THE AGGREGATE TRIPS FOR EACH MODE. /AUTHOR/

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 37 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.