Pemodelan Mortalitas dengan Pendekatan Single-Population Dan Multi-Population di Negara ASEAN

Utama, Anastasia Putri (2026) Pemodelan Mortalitas dengan Pendekatan Single-Population Dan Multi-Population di Negara ASEAN. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 5006221003-Undergraduate_Thesis.pdf] Text
5006221003-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only

Download (4MB) | Request a copy

Abstract

Pemodelan mortalitas memegang peran penting dalam manajemen risiko anuitas jiwa, dan dana pensiun. Proyeksi mortalitas yang tidak akurat dapat menyebabkan ketidaksesuaian kewajiban pembayaran di masa depan. Berbagai model telah dikembangkan untuk memprediksi mortalitas, salah satunya adalah model Lee-Carter, yang memodelkan mortalitas single population berdasarkan usia dan tren waktu. Seiring perkembangan model mortalitas, pendekatan multi-population diperkenalkan untuk memproyeksikan mortalitas beberapa populasi sekaligus dengan mempertimbangkan keterkaitan antar-populasi. Proyeksi mortalitas pada populasi mortalitas dapat diperkuat dengan informasi dari populasi lain yang memiliki karakteristik serupa. Salah satu pendekatan yang digunakan dalam pemodelan multi-populasi adalah hierarchical credibiltiy, yang merupakan pengembangan dari teori kredibilitas. Penelitian ini memodelkan mortalitas Indonesia, Malaysia, dan Thailand menggunakan model Lee-Carter sebagai pendekatan single-populiaton dan metode hierarchical credibility sebagai pendekatan multi-population. Data yang digunakan berupa central death rate dari United World Population Prospects (UN WPP) selama periode 1950-2023, mencakup tiga negara, dua jenis kelamin, serta kelompok usia 0 hingga 100 tahun. Evaluasi akurasi dilakukan menggunakan Mean Absolute Percentage Error (MAPE). Hasil pemodelan dengan pendekatan single-population menggunakan model Lee-Carter menunjukkan dinamika historis pada ketiga negara yang dapat ditangkap melalui parameter
================================================================================================================================
Mortality modeling plays a crucial role in managing risks in life annuities and pension funds. Inaccurate mortality projections can lead to mismatches in future payment obligations, particularly due to longevity risk. Various models have been developed to predict mortality, one of which is the Lee-Carter model, that models single-population mortality based on age and time trends. With the development of mortality modeling, multi-population approaches have been introduced to project mortality for multiple populations simultaneously while considering inter-population correlations. Mortality projections for a target population can be strengthened using information from other populations with similar characteristics. One approach used in multi-population modeling is hierarchical credibility, which is an extension of credibility theory. This study models the mortality of Indonesia, Malaysia, and Thailand using the Lee-Carter model as a single-population approach and the hierarchical credibility method as a multi- population approach.. The data used are central death rates from the United Nations World Population Prospects (UN WPP) during the period 1950-2023, covering three countries, two genders, and age groups from 0 to 100 years. The accuracy evaluation was conducted using the Mean Absolute Percentage Error (MAPE). The single-population modelling using the Lee- Carter model captures the historical dynamics of mortality in the three countries throught the parameter

Item Type: Thesis (Other)
Uncontrolled Keywords: Hierarchical Credibility, Lee-Carter, Mortalitas, Multi-population, Single-population Hierarchical Credibility, Lee-Carter, Mortality, Multi-population, Single-population
Subjects: Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry)
Q Science > QA Mathematics > QA280 Box-Jenkins forecasting
Q Science > QA Mathematics > QA401 Mathematical models.
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Actuaria > 94203-(S1) Undergraduate Thesis
Depositing User: Anastasia Putri Utama Putri Utama
Date Deposited: 12 Jan 2026 05:54
Last Modified: 12 Jan 2026 05:54
URI: http://repository.its.ac.id/id/eprint/129494

Actions (login required)

View Item View Item