David M. Zimmer

Copula Modeling: An Introduction for Practitioners

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 simulation-based approaches to joint modeling.

The Role of Copulas in the Housing Crisis

Due to its simplicity and familiarity, the Gaussian copula is popular in calculating risk in collaterized debt obligations, but it imposes asymptotic independence such that extreme events appear to be unrelated. This restriction might be innocuous in normal times, but during extreme events, such as the housing crisis, the Gaussian copula might be inappropriate. This paper explores various copula specifications and finds that the degree to which housing prices are related based on the Gaussian copula is too small compared with real housing price data.

COST-OFFSETS OF PRESCRIPTION DRUG EXPENDITURES: DATA ANALYSIS VIA A COPULA-BASED BIVARIATE DYNAMIC HURDLE MODEL

In this paper, we estimate a copula-based bivariate dynamic hurdle model of prescription drug and nondrug expenditures to test the cost-offset hypothesis, which posits that increased expenditures on prescription drugs are offset by reductions in other nondrug expenditures. We apply the proposed methodology to data from the Medical Expenditure Panel Survey, which have the following features: (i) the observed bivariate outcomes are a mixture of zeros and continuously measured positives; (ii) both the zero and positive outcomes show state dependence and inter-temporal interdependence; and (iii) the zeros and the positives display contemporaneous association. The point mass at zero is accommodated using a hurdle or a two-part approach. The copula-based approach to generating joint distributions is appealing because the contemporaneous association involves asymmetric dependence. The paper studies samples categorized by four health conditions: arthritis, diabetes, heart disease, and mental illness. There is evidence of greater than dollar-for-dollar cost-offsets of expenditures on prescribed drugs for relatively low levels of spending on drugs and less than dollar-for-dollar cost-offsets at higher levels of drug expenditures.

The effect of Medicare Part D on prescription drug composition and demand

Purpose - – The US Medicare Modernization Act of 2003 introduced optional prescription drug coverage, beginning in 2006, widely known as Medicare Part D. This paper uses up-to-date nationally representative survey data to investigate the impact of Part D not only on drug spending and consumption, but also on the composition of drug consumption. The paper aims to discuss these issues. Design/methodology/approach - – Specifically, the paper investigates whether Part D impacted the number of therapeutic classes for which drugs were prescribed, and also whether Part D lead to increased usage of drugs for specific medical conditions that typically receive drug-intensive therapies. Findings - – In addition to confirming findings from previous studies, this paper shows that Part D increased the number of therapeutic classes to which seniors receive drugs by approximately four classes. Part D also lead to increased usage of drugs used to treat upper respiratory disease, hypertension, and diabetes. Originality/value - – While mostly concurring with previous studies on the spending impacts of Part D, this paper is the first to shed light on other impacts of Part D, specifically with respect to its impact on therapeutic classes for which drugs are prescribed.

THE RELATIONSHIP BETWEEN STUDENT TRANSFERS AND DISTRICT ACADEMIC PERFORMANCE: ACCOUNTING FOR FEEDBACK EFFECTS

This paper draws attention to a subtle, but concerning, empirical challenge common in panel data models that seek to estimate the relationship between student transfers and district academic performance. Specifically, if such models have a dynamic element, and if the estimator controls for unobserved traits by including district-level effects, then model validity does not allow for a districts academic performance, in turn, to impact future transfers. Yet it seems reasonable that families, having access to publicly available aggregated information on standardized test results, seek to move their children to better-performing districts. In this paper, we demonstrate that, not only is such feedback quantitatively and qualitatively important, but also that allowing for such feedback substantially alters the estimated relationship between transfers and district performance.

The Effect of the Consolidated Omnibus Reconciliation Act of 1985 on Health Care Utilization of Employment Separators

Abstract This paper uses data from the Medical Expenditure Panel Survey to estimate the effect of COBRA on health care utilization among a sample of individuals who experience employment separation. The empirical specification employs a structural simultaneous equations model of insurance choice and utilization that is estimated by Maximum Simulated Likelihood. Results indicate that employment separators who elect COBRA appear to consume more health care compared to individuals who become temporarily uninsured. In addition, results do not indicate adverse selection into COBRA. Although COBRA enrollees consume more health care than temporary insurance losers, election appears to exhibit favorable selection with respect to physician utilization.

Does COBRA reduce the probability that job separators return to work

This study examines a decade of individual-level US employment and insurance information to investigate whether federally mandated Consolidated Omnibus Reconciliation Act (COBRA) regulation affects post-separation employment activity. The empirical approach addresses the possibility that COBRA enrollment is endogenous with respect to post-separation employment outcomes. The main finding is that, although COBRA enrollees are 5 percentage points less likely to become re-employed, this relationship is not causal. Rather, individuals with lower probabilities of becoming re-employed tend to enroll in COBRA. The reason appears to be because, when compared to subjects who voluntarily leave for other jobs, subjects who separate for other reasons not only are less likely to become re-employed, but they also are approximately 23% more likely to enroll in COBRA.

Predicting Price Effects from Retail Mergers

We propose a simple method for predicting price effects from mergers between branded retail chains competing in many local markets. When past mergers created markets with the same number of brands but different numbers of brand owners, price data at a single point in time exhibit between-market variation much like the variation over time from mergers. We construct an estimator isolating this between-market variation and use it to predict price effects from mergers in the car rental industry.

DOES COBRA'S RETROACTIVE COVERAGE FEATURE ENCOURAGE DELAYED ENROLLMENT?

The Consolidated Omnibus Reconciliation Act (COBRA) of 1985, which aimed to protect individuals experiencing employment separation from losing employer‐provided health insurance, contains a feature that is unusual among health insurance markets. Individuals eligible for COBRA have 60 days following employment separation to elect coverage, and if they elect, coverage is retroactive back to the date of employment separation. This paper investigates whether employment separators take advantage of COBRAs retroactive coverage provision by delaying enrollment until after incurring medical expenses. Results indicate that an individual whose household incurs medical expenses during the months after employment separation is approximately 1−10 percentage points more likely to subsequently enroll in COBRA, depending on the magnitude of expenses.

Modelling bivariate count distributions with finite mixture models: application to health care demand of married couples

Count measures of health care utilization are often correlated with other measures of utilization. In addition, utilization measures display a high proportion of zero observations. This article attempts to accommodate both data features in one model, with an application to medical care usage of husbands and wives. A bivariate count representation is used to model dependence between husbands’ and wives’ utilizations, and a finite mixture specification accommodates the problem of excess zeros. Results show that married couples are characterized by two distinct subpopulations according to the intensity of utilization of the wife.