Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


ysu1329508121.pdf (517.07 KB)

ETD Abstract Container

Abstract Header

Comparison of Logistic Force of Mortality Models for Predicting Life Table Probabilities of Death: A Simulation-Based Approach

Eynon, James R.
http://rave.ohiolink.edu/etdc/view?acc_num=ysu1329508121

Abstract Details

2011, Master of Science in Mathematics, Youngstown State University, Department of Mathematics and Statistics.
A program was written in the statistical software package R for conducting Monte Carlo studies based on simulated life tables, and then used in a study to compare two different models for predicting life table probabilities of death. A parametric probability model was used by the program to generate the cohort distribution of deaths, based on supplied life table data. For the present study a cohort life table was constructed using mortality data from the Social Security Death Index, Master File. The models evaluated in the present Monte Carlo study are alternative three-parameter versions of the logistic force of mortality model. The models were fit to simulated life table data for ages 80 to 99, and then used to make probability of death predictions for ages 80 to 105. The Monte Carlo simulations were used to obtain the average values and standard deviations of the probability of death predictions generated by the two models, which were then compared to one another and to the actual probabilities of death based on the probability model that generated the simulated life table data. Results of the simulations showed that the mean probabilities of death predicted by the two models were very similar over the range of ages considered, but usually deviated somewhat from the actual probabilities of death. In the age range of 80-99, the average percentage deviation was less than 2% for each model, while in the age range of 100-105, the average percentage deviation for the models was around 5-6%. In the age range of 100-105, both models always underestimated the true probability of death.
Thomas Wakefield, PhD (Advisor)
G. Andy Chang, PhD (Committee Member)
Richard Burden, PhD (Committee Member)
78 p.
Aging; Applied Mathematics; Demographics; Statistics
Logistic force of mortality models; Monte Carlo simulation; Life table probability of death; Social Security Death Index

Recommended Citations

Citations

  • Eynon, J. R. (2011). Comparison of Logistic Force of Mortality Models for Predicting Life Table Probabilities of Death: A Simulation-Based Approach [Master's thesis, Youngstown State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ysu1329508121

    APA Style (7th edition)

  • Eynon, James. Comparison of Logistic Force of Mortality Models for Predicting Life Table Probabilities of Death: A Simulation-Based Approach. 2011. Youngstown State University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=ysu1329508121.

    MLA Style (8th edition)

  • Eynon, James. "Comparison of Logistic Force of Mortality Models for Predicting Life Table Probabilities of Death: A Simulation-Based Approach." Master's thesis, Youngstown State University, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=ysu1329508121

    Chicago Manual of Style (17th edition)

ysu1329508121
553
© 2011, all rights reserved.
This open access ETD is published by Youngstown State University and OhioLINK.