Are intrazonal trips ignorable?

Intrazonal trips are not always included in model estimation because they do not appear on a network in centroid-to-centroid travel. It is also presumed that their exclusion does not affect model results. This paper tests the above presumption by examining the assumptions of ignorable missingness. The results indicate that omitting intrazonal trips in model estimation results in biased sample. Consequently, parameter estimates get biased. The paper also compares the results of travel mode choice models by excluding and including the intrazonal trips in model estimation.