Economic Perspective of Transferability of Mode Choice Models

Abstract

Economic analysis between the increment of accuracy and the number of small sample size was conducted to the spatial transferability in Ho Chi Minh City. Transfer index generated from the association of small sized samples with naive method, updating alternative specific constants, Bayesian updating, updating alternative specific constants and scale parameter, and combined transfer estimator were used to represent the accuracy in the analysis. Graphical observation based on marginal transfer index and increment of marginal transfer index was used to produce the optimum range. In general, the economic range produced by the first three methods is between 150 and 360 observations. However, there is no optimum range need to be constructed from the last two methods as the transfer index is relatively established. A sample of 100 observations is recommended as the cost)effective sample size for these two methods. These monetary findings are not in line with the result from previous study.

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 — 3 citations exist upstream.

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