Description: When setting reserves, multiple methods are often used in the creation of the reserve estimate. Judgment is warranted to combine these different estimates into a final recommendation. This paper describes two techniques that can be used to combine these estimates that may result in better accuracy and lower variance.

Description: From a session at the Spring regional meeting of the Society of Actuaries held in Atlanta, Georgia, May 24-25, 1999 Year 2000 and Beyond: Society of Actuaries New Course: Applied Modeling Demonstration Charts 5 & 6 from that presentation

Description: Health Watch, Issue 79, December 2015, Health Watch

Description: This article describes a method that can be useful when re-fitting a risk score model to a population of only moderate size. Learn how to use concepts like ridge regression to train a model with partial credibility.

Description: First article in a series that walks through the progression from developing LTC assumptions using traditional methods to doing so using predictive analytics.

Description: This article compares three potential approaches to determining new coefficients for health-based risk scoring models: full recalibration, p-value credibility weighting, and penalized ridge regression.

Description: Nonparametric regression tries to ?nd a relationship between the predictor and the response without assuming shape of estimated regression function. Its theory and methods are well developed for the case of completely observed vectors of predictors and responses. In many applications, including actuarial, some components of the observed vectors may be missed. Ignoring missing data and using known methods of nonparametric regression may yield inconsistent estimation. Theoretical results on optimal nonparametric regression with missing data are presented, and an applied actuarial example is discussed.

Description: Third article in a series on how to use predictive analytics to improve the development of long-term care projection assumptions.

Description: An approach to quantify medical intervention savings when medical claims data is not available by leveraging overlapping measurement techniques.

Description: This paper outlines a method of parametric modeling that may be used to produce forecasts and forecast intervals that will convey a measure of the reliance that may be placed on the forecasts. Followed by 2 discussion papers submitted