HETEROGENEITY, EXCESS ZEROS, AND THE STRUCTURE OF COUNT DATA MODELS
โ Scribed by JOHN MULLAHY
- Publisher
- John Wiley and Sons
- Year
- 1997
- Tongue
- English
- Weight
- 209 KB
- Volume
- 12
- Category
- Article
- ISSN
- 0883-7252
No coin nor oath required. For personal study only.
โฆ Synopsis
This paper demonstrates that the unobserved heterogeneity commonly assumed to be the source of overdispersion in count data models has predictable implications for the probability structure of such mixture models. In particular, the common observation of excess zeros is a strict implication of unobserved heterogeneity. This result has important implications for using count model estimates for predicting certain interesting parameters. Test statistics to detect such heterogeneity-related departures from the null model are proposed and applied in a health-care utilization example, suggesting that a null Poisson model should be rejected in favour of a mixed alternative.
๐ SIMILAR VOLUMES
13C- and 57Fe-NMR spectra of several carbon monoxide hemoprotein models with varying polar and steric effects of the distal organic superstructure, constraints of the proximal side, and solvent polarity are reported. The 13C shieldings of heme models cover a 4.0 ppm range that is extended to 7.0 ppm