Abstract
This paper presents a discrete choice modeling framework for analysis of repeated choices associated with expensive automobile insurance policy (AIP) — the bundled physical damage coverage and the number of consecutive years the insured has purchased the same type of AIP. A four-year panel data with 9,949 voluntary automobile insurance records, randomly drawn from a non-life insurance company in Taiwan, is used to test the empirical case. The estimation results of the preferred multinomial logit model show that engine capacity and vehicle make significantly affect selection of AIP bundles. Older adults and owners of newer vehicles, of larger engine capacities, and of imported vehicles tend to repeat purchase expensive AIP bundles for three or four consecutive years. The preferred nested logit model further confirms that the inertia of the same individuals leads to repeat buying of the same physical damage coverage policies for several consecutive years.
