Logistic Regression for Insured Mortality Experience Studies

North American Actuarial Journal, 19.4 (2015): 241-255.

19 Pages Posted: 10 Jul 2020

See all articles by Zhi Li

Zhi Li

Taiping Insurance Group - Business Management Dept.

Date Written: 2015

Abstract

Properly adapted statistical modeling methodology can be a powerful tool for coping with a broad range of challenges related to life and annuity insurance industries’ experience studies. In this paper, we present a logistic regression model based U.S. insured mortality experience study with a focus on gaining study efficiency and effectiveness by addressing multiple analytical predicaments within one statistical modeling framework. These predicaments include but not limit to: a) test statistical significances or credibility of potential mortality drivers; b) estimate normalized mortality, slopes, and differentials; c) quantify study reliability; and d) extrapolate for under-experienced mortality, smooth between select and ultimate estimations, and assist basic experience table developments.

Suggested Citation

Li, Zhi, Logistic Regression for Insured Mortality Experience Studies (2015). North American Actuarial Journal, 19.4 (2015): 241-255. , Available at SSRN: https://ssrn.com/abstract=3629979

Zhi Li (Contact Author)

Taiping Insurance Group - Business Management Dept. ( email )

18 King Wah Road, Noith Point
Hong Kong
Hong Kong
852-59830519 (Phone)

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
31
Abstract Views
456
PlumX Metrics