This article explores the copula approach for econometric modeling of joint parametric distributions. Although theoretical foundations of copulas are complex, this paper demonstrates that practical implementation and estimation are relatively straightforward. An attractive feature of parametrically specified copulas is that estimation and inference are based on standard maximum likelihood procedures, and thus copulas can be estimated using desktop econometric software. This represents a substantial advantage of copulas over recently proposed simulationbased approaches to joint modeling.

/pdf/copula-modeling-an-introduction-for-practitioners-1fcatpzmuu.pdf

Copula Modeling: An Introduction for Practitioners

Informal care and health care use of older adults.

The decision to contact a physician and the decision about how often to contact a physician are determined by different decisionmakers. We introduce a negative binomial distributed hurdle model that specifies the two stages of the decisionmaking process as different stochastic processes, while at the same time taking care of the discrete nature of the data. Empirical results are based on a cross-section of the West German Socioeconomic Panel. Specification tests reveal that the two stages of the process need to be treated as two distinct processes. This, in turn, implies that ignoring this distinction leads to serious misinterpretation.

An Econometric Model of the Two-Part Decision Process in the Demand for Health

SUMMARY In this article we develop a finite mixture negative binomial count model that accommodates unobserved heterogeneity in an intuitive and analytically tractable manner. This model, the standard negative binomial model, and its hurdle extension are estimated for six measures of medical care demand by the elderly using a sample from the 1987 National Medical Expenditure Survey. The finite mixture model is preferred overall by statistical model selection criteria. Two points of support adequately describe the distribution of the unobserved heterogeneity, suggesting two latent populations, the ‘healthy’ and the ‘ill’ whose fitted distributions diAer substantially from each other. #1997 by John Wiley & Sons, Ltd.

/pdf/demand-for-medical-care-by-the-elderly-a-finite-mixture-3po7oxqvzp.pdf

Demand for medical care by the elderly: a finite mixture approach

Adverse selection is perceived to be a major source of market failure in insurance markets. There is little empirical evidence on the extent of the problem. We estimate a structural model of health insurance and health care choices using data on single individuals from the NMES. A robust prediction of adverse-selection models is that riskier types buy more coverage and, on average, end up using more care. We test for unobservables linking health insurance status and health care consumption. We find no evidence of informational asymmetries.

https://www.jstor.org/stable/pdfplus/2696362.pdf

Asymmetric information in health insurance: evidence from the National Medical Expenditure Survey.

This paper develops a model for interdependent demand for health insurance and health care under uncertainty to throw light on the issue of insurance-induced distortions in the demand for health care services. The model is used to empirically analyse the determinants of the choice of health insurance type and seven types of health care services using micro-level data from the 1977–78 Australian Health Survey. Econometric implementation of the model involves, simultaneously, issues of discreteness of choice, selectivity and stochastic dependence between health insurance and utilization. Health status appears to be more important in determining health care service use than health insurance choice, while income appears to be more important in determining health insurance choice than in determining health care service use. For a broad range of health care services both moral hazard and self selection are found to be important determinants of utilization of health care services.

https://www.jstor.org/stable/pdfplus/2297531.pdf

A Microeconometric Model of the Demand for Health Care and Health Insurance in Australia

The Information Matrix Test and Its Implied Alternative Hypotheses

Conditional Moment Tests With Explicit Alternative

This paper makes three contributions. First, it uses copula functions to obtain a flexible bivariate parametric model for nonnegative integer-valued data (counts). Second, it recovers the distribution of the difference in the two counts from a specifed bivariate count distribution. Third, the methods are applied to counts that are measured with error. Specifically we model the determinants of the difference between the self-reported number of doctor visits (measured with error) and true number of doctor visits (also available in the data used).

A. Cameron

Papers

A Microeconometric Model of the Demand for Health Care and Health Insurance in Australia

The Information Matrix Test and Its Implied Alternative Hypotheses

Conditional Moment Tests With Explicit Alternative

Modeling the Differences in Counted Outcomes using Bivariate Copula Models: with Application to Mismeasured Counts