Search

Using only social determinants, we employ an unsupervised clustering methodology that can differentiate high and low expenditure individuals. There are three major implications of this work: (1) cl...

This study examines the causal effect of delayed oral health care on increased emergency department visits in the United States. We extend prior research by estimating the effect of delayed or forg...

High utilizers of health care are those individuals in the upper tail of the distribution each year. The main purpose of our work is to identify determinants of persistent high utilizers in adults,...

Many health plans and employers gather information about their enrollees in the form of self-reported surveys. This information is useful in assessing the risk pool of the population, targeting dis...

This article extends the standard two-part model for predicting health care expenditures to the case where multiple events may occur within a one-year period. The first part of the extended model represents the frequency of events, such as the number of inpatient hospital stays or outpatient visits, and the second part models expenditure per event. Both component models also use independent variables that consist of an individual’s demographic and access characteristics, socioeconomic status, health status, health insurance coverage, employment status, and industry classification. The second part of the model also includes a variable representing the number of events to predict the expenditure per event, thus capturing dependencies between the first and second parts. This article introduces closed-form predictors of annual total expenditures and demonstrates how to create simulated predictive distributions for individuals and groups. The data for this study are from the Medical Expenditure Panel ...

Health care expenditures have accounted for increasing proportions of the U.S. gross domestic product, and the rate of growth of health care expenditures has increased over the past two decades. These two measures of assessing whether the level of health care expenditures is affordable may be appropriate in the aggregate for the United States but are not appropriate to assess whether individual stakeholder groups can afford their particular level of spending on health care. Health care is an economic good that differs from other economic goods, as it involves life and death issues, and invokes a call for a moral authority. This article explores definitions of what is affordable health care from the perspective of different stakeholders and suggests that other measures are needed to assess whether or not health care is affordable for stakeholders as one definition is not appropriate for all stakeholders. INTRODUCTION Financial forecasts for U.S. health care spending have led to concerns as to whether the economy can sustain this growth in the future, or whether there is a potential crisis in the level of health care spending today. Two common measures used to indicate that the U.S. health care spending is not affordable with regard to the level of aggregate spending are: a growing percentage of gross domestic product (GDP) devoted to health care and increasing rates of growth of health care spending. What is overlooked in these measures is whether they are applicable to different stakeholder groups or stakeholders at an individual level and what financial impact they may have on stakeholders. Stakeholders are health care providers, private payers such as insurers, public payers such as governmental entities, employers, and consumers who utilize the services, who also may pay some or all of the premiums, and may also pay the providers. This article will address these stakeholder perspectives and suggest that their perspectives are critical to the discussion of whether or not health care is affordable. As background, in 1960, U.S. National Health Expenditures (NHE) were 5.2 percent of the U.S. GDP, while in 2005, NHE were 16 percent of GDP (Centers for Medicare & Medicaid Services, 2007). The Office of the Actuary at the Centers for Medicare and Medicaid Services (CMS) developed macro-level models for projecting short-term and long-term health care spending for the U.S. economy (Braden et al., 1998; Smith et al., 1999; Seiden et al., 2001). Short-term national-level forecasts from CMS estimate growth in NHE to $3.6 trillion in 2014, or 18.7 percent of GDP (Heffler et al., 2005). By 2014, the public sector is estimated to account for half of total health care spending (Centers for Medicare & Medicaid Services, 2007). Intermediate-term projections using the CMS methodology indicated that NHE would increase to $16.0 trillion by 2030, or 32 percent of GDP. The average nominal annual growth rate of NHE was projected as 8.3 percent from 1990 to 2030, while the projected real annual NHE growth rate was about 3.0 percent (Burner et al., 1992). Chernew et al. (2003) suggested two alternative definitions for health care affordability in the aggregate. The first definition examined the difference between national income and a level of nonhealth care spending. If the difference was positive, then health care spending was deemed to be affordable. A second definition, admittedly more conservative, examined whether a proportion of the increase in income could be spent on health care. Either definition would allow the absolute amount of money spent on health care to rise with income. Their article utilized the second definition to be consistent with a Medicare Technical Review panel that assumed there would never be a downward trend in nonhealth care spending. Their conclusions were that aggregate health care expenditures would be affordable until 2075 if real annual NHE grew at a rate 1 percentage point higher than real annual GDP, even though aggregate health care expenditures would consume 38 percent of GDP. …

In this paper, we consider “heavy-tailed” data, that is, data where extreme values are likely to occur. Heavy-tailed data have been analyzed using flexible distributions such as the generalized beta of the second kind, the generalized gamma and the Burr. These distributions allow us to handle data with either positive or negative skewness, as well as heavy tails. Moreover, it has been shown that they can also accommodate cross-sectional regression models by allowing functions of explanatory variables to serve as distribution parameters. The objective of this paper is to extend this literature to accommodate longitudinal data, where one observes repeated observations of cross-sectional data. Specifically, we use copulas to model the dependencies over time, and heavy-tailed regression models to represent the marginal distributions. We also introduce model exploration techniques to help us with the initial choice of the copula and a goodness-of-fit test of elliptical copulas for model validation. In a longitudinal data context, we argue that elliptical copulas will be typically preferred to the Archimedean copulas. To illustrate our methods, Wisconsin nursing homes utilization data from 1995 to 2001 are analyzed. These data exhibit long tails and negative skewness and so help us to motivate the need for our new techniques. We find that time and the nursing home facility size as measured through the number of beds and square footage are important predictors of future utilization. Moreover, using our parametric model, we provide not only point predictions but also an entire predictive distribution.

Chronic diseases account for 75% of U.S. national health care expenditures as estimated by the Centers for Disease Control. Many chronic diseases are punctuated by acute episodes of illnesses that occur randomly and create cost spikes in utilization from one year to the next. Modeling to account for these random events provides better estimates of (1) future costs and (2) their variability. A Bayesian statistical model is used to predict the incidence and cost of hospitalizations for one chronic disease. A two-part statistical model is described that separately models the utilization and cost of hospitalization. Individual demographic characteristics are included as well as a simple biological classification system to adjust for the severity of disease among individuals. Results by child, as well as by calendar year, are presented. Using a simple approach to incorporate severity, the model produces reasonable estimates of the number of hospitalizations and cost of hospitalization for the group in...

The recent development and availability of sophisticated computer software has facilitated the use of predictive modeling by actuaries and other financial analysts. Predictive modeling has been used for several applications in both the health and property and casualty sectors. Often these applications employ extensions of industry-specific techniques and do not make full use of information contained in the data. In contrast, we employ fundamental statistical methods for predictive modeling that can be used in a variety of disciplines. As demonstrated in this article, this methodology permits a disciplined approach to model building, including model development and validation phases. This article is intended as a tutorial for the analyst interested in using predictive modeling by making the process more transparent. This article illustrates the predictive modeling process using State of Wisconsin nursing home cost reports. We examine utilization of approximately 400 nursing homes from 1989 to 2001...

This paper is an extension of earlier work (Rosenberg 1998; Rosenberg, Andrews, and Lenk 1999; Rosenberg and Griffith 2000) that introduced a statistical control model to supplement current efforts inexpensively to help reduce unnecessary expenditures. The application of the study was to predict the rate of nonacceptable inpatient claims (NACs). In that work, a statistical model was proposed to link information obtained through an expensive audit with inexpensive information that is readily available to estimate the probability that a claim is a NAC. The premise was that a statistical system can be developed to supplement the expensive audit for additional control between audits. Estimates of the NAC rate obtained from the statistical model are used as input in a statistical monitor to assess whether the NAC rate had changed over time. The statistical monitor is the subject of this paper. The idea is that subgroups of claims can be analyzed inexpensively with the statistical monitor to determine ...

This paper explores the use of Bayesian models to analyze time series data. The Bayesian approach produces output that can be readily understood by actuaries and included in their own experience studies. We illustrate this Bayesian approach by analyzing U.S. unemployment rates, a macroeconomic time series. Understanding time series of macroeconomic variables can help actuaries in pricing and reserving their products. For example, a change in the level and/or variance of the unemployment series is of interest to actuaries, because its movement can explain a changing pattern of lapse rates of incidence rates. Our Bayesian analysis, based on models developed by McCulloch and Tsay (1993, 1994), allows for shifts in the level and in the error variance of a process. We develop a measure of model fit, based on the Akaike Information Criterion, that can be used in choosing between alternative models. Posterior prediction intervals for the fitted values are also created to pictorially show the range of pa...

A nonacceptable claim (NAC) is an insurance claim for an unnecessary hospital stay. This study establishes a statistical model that predicts the NAC rate. The model supplements current insurer programs that rely on detailed audits of patient medical records. Hospital discharge claim records are used as inputs in the statistical model to predict retrospectively the probability that a hospital admission is nonacceptable. A full Bayesian hierarchical logistic regression model is used with regression coefficients that are random across the primary diagnosis codes. The model provides better fits and predictions than standard methods that pool across primary diagnosis codes.

This paper presents a forecasting model of economic assumptions that are inputs to projections of the Social Security system. Social Security projections are made to help policy-makers understand the financial stability of the system. Because system income and expenditures are subject to changes in law, they are controllable and not readily amenable to forecasting techniques. Hence, we focus directly on the four major economic assumptions to the system: inflation rate, investment returns, wage rate, and unemployment rate. Population models, the other major input to Social Security projections, require special demographic techniques and are not addressed here. Our approach to developing a forecasting model emphasizes exploring characteristics of the data. That is, we use graphical techniques and diagnostic statistics to display patterns that are evident in the data. These patterns include (1) serial correlation, (2) conditional heteroscedasticity, (3) contemporaneous correlations, and (4) cross-co...