شماره ركورد كنفرانس
5191
عنوان مقاله
Modeling and Forecasting Mortality Rate with Cohort Effect andOverdispersion
پديدآورندگان
Roshani Amin Department of Statistics, Razi University, Kermanshah, Iran , Izadi Muhyiddin Department of Statistics, Razi University, Kermanshah, Iran , Khaledi Baha-Eldin Department of Applied Statistics and Research Methods, University of Northern Colorado, Greeley, CO 80636, USA
تعداد صفحه
7
كليدواژه
Bayesian methods , Hamiltonian Monte Carlo , Poisson Lee , Carter mortalitymodel , Time series prediction.
سال انتشار
1401
عنوان كنفرانس
شانزدهمين كنفرانس آمار ايران
زبان مدرك
انگليسي
چكيده فارسي
In this paper, we present an extension of the Poisson Lee-Carter model for predicting mortality rates that includes the cohort effect and an overdispersion component. To compute the estimation of the model parameters and mortality rate predictions, we use Bayesian analysis and the No-U-Turn sampler (NUTS), which is an extension of Hamiltonian Monte Carlo (HMC). We compare the prediction accuracy of the proposed model and the Poisson Log-Normal Lee-Carter (PLNLC) model using real mortality data from several European countries. We conclude that the proposed model dominates the PLNLC model.
كشور
ايران
لينک به اين مدرک