All Rights Reserved
AccessEcon LLC 2006, 2008.
Powered by MinhViet JSC
ralph lauren polo

 
Hiroaki Masuhara
 
''Multi-episode count data estimation for health care demand''
( 2021, Vol. 41 No.4 )
 
 
This study proposes new multi-episode count data models for health care analysis. Using the Pólya-Aeppli distribution, a Poisson process for seeking medical care and a geometric process for the number of treatments are specified. Moreover, this paper introduces unobserved heterogeneities to both Poisson and geometric processes. Using the National Medical Expenditure Survey, the proposed models demonstrate good performance and the large differences in estimated coefficients compared with conventional hurdle and finite mixture count data models. It is useful to apply the multi-episode count data models proposed in this paper.
 
 
Keywords: count data; multi-episode; geometric distribution; health care demand; finite mixture model; hurdle (two-part) model
JEL: C3 - Cross-Sectional Models; Spatial Models; Treatment Effect Models; Quantile Regressions
C2 - Single Equation Models; Single Variables: General
 
Manuscript Received : Sep 10 2021 Manuscript Accepted : Dec 29 2021

  This abstract has been downloaded 156 times                The Full PDF of this paper has been downloaded 140901 times