This paper shows how to use a statistical measure, the coefficient of determination, for quantifying the relative importance of a source of uncertainty. With a quantitative measure of relative importance, risk managers can sharpen their intuition about the relative importance of risk factors and become better custodians of financial security systems. This paper shows that the coefficient of determination is intuitively appealing in assessing the effectiveness of basic risk management techniques including risk exchange, pooling, and financial risk management. From NAAJ, April 1998, Volume 2, Number 2.

In this paper, we examine case studies from three different areas of insurance practice: health care, workers' compensation, and group term life. These different case studies illustrate how the broad class of panel data models can be applied to different functional areas and to data that have different features. From NAAJ, October 2001, Volume 5, Number 4.

In most countries, females live several years longer than males. Many biological and behavioral reasons have been presented in the scientific literature to explain this “female advantage.” A cross-sectional regression study, using 45 explanatory variables and data collected from 169 countries, provides support to the behavioral hypothesis. From NAAJ, October 2002, Volume 6, Number 4.

This case study illustrates the analysis of two possible regression models for bivariate claims data. A comparison of the analyses reveals that forecasted total losses can be dramatically underestimated by the maximum likelihood estimation method because it ignores the inherent parameter uncertainty. From NAAJ, October 2002, Volume 6, Number 4.

This abstract describes a paper in which several issues surrounding the 2011 paper “Copula Regression”, Variance volume 5-issue1, by Rahul A. Parsa and Stuart A. Klugman, are discussed.

Presentation from the 2009 Health Spring Meeting moderated by Mr. Kane. Predictive models continue to gain traction within healthcare organizations for a broad range of financial and actuarial applications. Some are out–of–the–box, commercially available predictive models that had their roots in academic research. Others have been developed entirely by in–house researchers coming from a wide range of disciplines. Still others are based on a hybrid model where commercially available models have been recalibrated using other data sources within the enterprise. Finally, the output from predictive models may be used as an input to an entirely separate modeling process. Several case studies will be presented where speakers will discuss how the research process led to selection, recalibration, or creation of a hybrid predictive model. Why was one model chosen over another, and what factors were deemed significant in the model building process? Did modelers have to balance considerations between data availability, model practicality, and parsimony? Were models developed with the end stakeholders and specific business applications in mind? Or do stakeholders try to force an existing model to be the mother of all business solutions?

A panel discussion moderated by Tia Goss Sawhney from the 2008 Individual and Small Group Health Insurance Underwriting Seminar We will explore the use of predictive modeling in underwriting. The moderator will give some brief introductory comments defining predictive modeling and distinguishing between predictive modeling and automated rules systems. Predictive modeling experts will give mini-presentations that address the following issues: 1. How is predictive modeling being used in health insurance underwriting today? 2. Have they been successful? Less than successful? 3. What will future models be able to do? 4. What projects are currently underway? Based on their business perspective, an actuary and an underwriter will then challenge the experts. Finally, we will open the panel to questions to the floor.

Employee termination and retirement probabilities affect the valuation of employee benefit plans and thus are of concern to actuaries. To provide timely experience for the profession, the Society of Actuaries’ Non-Mortality Decrements Task Force organized a data collection effort. Thirty-two contributors provided over 1.7 million life years of pension plan turnover data for years 1994-2000. This study summarizes the results of this data collection effort.

The Johns Hopkins ACG Team's comments regarding their participation in the Comparative Analysis of Claims-Based Tools for Health Risk Assessment.

Research report that explores key factors associated with an insurer’s reputational risk and conditions that would generate incentives for insurers to behave in a way that causes loss of their positive reputation.