The Usage of State Space Models in Mortality Modeling and Predictions
In demography, mortality modeling with respect to age and time dimensions is often associated with the traditionally used Lee-Carter model. The Lee-Carter model considers a constant set of parameters of agespecific mortality change for forecasts, which can lead to the problem of overcoming the biode...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Czech Statistical Office
2023-03-01
|
| Series: | Statistika: Statistics and Economy Journal |
| Subjects: | |
| Online Access: | https://www.czso.cz/documents/10180/192164336/32019723q1_121_131_matejka_analyses.pdf/c7bd01ea-28e0-48e7-85a0-ba6caec3fcea?version=1.2 |
| _version_ | 1797866358109634560 |
|---|---|
| author | Martin Matějka Ivana Malá |
| author_facet | Martin Matějka Ivana Malá |
| author_sort | Martin Matějka |
| collection | DOAJ |
| description | In demography, mortality modeling with respect to age and time dimensions is often associated with the traditionally used Lee-Carter model. The Lee-Carter model considers a constant set of parameters of agespecific mortality change for forecasts, which can lead to the problem of overcoming the biodemographic limit. The main motivation of this paper is the use of more flexible models for mortality modeling. The paper explores the use of state space models for modeling and predicting mortality in a form not typically used in demography. In this context, it is a generalized Poisson state space model with overdispersion parameters. Concerning the empirical results, a comparison is made between the predictive abilities of the Lee-Carter and the generalized Poisson state space model with overdispersion parameters. The state space Poisson model with overdispersion parameters led to better results with respect to the comparison of modeled and historical observations. However, when comparing the predictions in the cross-validation area, both models were represented with similar overall mean squared error. |
| first_indexed | 2024-04-09T23:22:51Z |
| format | Article |
| id | doaj.art-4f122d802db7465597388936ae4b64bf |
| institution | Directory Open Access Journal |
| issn | 0322-788X 1804-8765 |
| language | English |
| last_indexed | 2024-04-09T23:22:51Z |
| publishDate | 2023-03-01 |
| publisher | Czech Statistical Office |
| record_format | Article |
| series | Statistika: Statistics and Economy Journal |
| spelling | doaj.art-4f122d802db7465597388936ae4b64bf2023-03-21T12:16:19ZengCzech Statistical OfficeStatistika: Statistics and Economy Journal0322-788X1804-87652023-03-01103112113110.54694/stat.2022.33The Usage of State Space Models in Mortality Modeling and PredictionsMartin Matějka0Ivana Malá1Prague University of Economics and Business, Prague, Czech RepublicPrague University of Economics and Business, Prague, Czech RepublicIn demography, mortality modeling with respect to age and time dimensions is often associated with the traditionally used Lee-Carter model. The Lee-Carter model considers a constant set of parameters of agespecific mortality change for forecasts, which can lead to the problem of overcoming the biodemographic limit. The main motivation of this paper is the use of more flexible models for mortality modeling. The paper explores the use of state space models for modeling and predicting mortality in a form not typically used in demography. In this context, it is a generalized Poisson state space model with overdispersion parameters. Concerning the empirical results, a comparison is made between the predictive abilities of the Lee-Carter and the generalized Poisson state space model with overdispersion parameters. The state space Poisson model with overdispersion parameters led to better results with respect to the comparison of modeled and historical observations. However, when comparing the predictions in the cross-validation area, both models were represented with similar overall mean squared error.https://www.czso.cz/documents/10180/192164336/32019723q1_121_131_matejka_analyses.pdf/c7bd01ea-28e0-48e7-85a0-ba6caec3fcea?version=1.2generalized state space modelsextended kalman filterexponential smoothinglee-carter modelmortalityprediction comparison |
| spellingShingle | Martin Matějka Ivana Malá The Usage of State Space Models in Mortality Modeling and Predictions Statistika: Statistics and Economy Journal generalized state space models extended kalman filter exponential smoothing lee-carter model mortality prediction comparison |
| title | The Usage of State Space Models in Mortality Modeling and Predictions |
| title_full | The Usage of State Space Models in Mortality Modeling and Predictions |
| title_fullStr | The Usage of State Space Models in Mortality Modeling and Predictions |
| title_full_unstemmed | The Usage of State Space Models in Mortality Modeling and Predictions |
| title_short | The Usage of State Space Models in Mortality Modeling and Predictions |
| title_sort | usage of state space models in mortality modeling and predictions |
| topic | generalized state space models extended kalman filter exponential smoothing lee-carter model mortality prediction comparison |
| url | https://www.czso.cz/documents/10180/192164336/32019723q1_121_131_matejka_analyses.pdf/c7bd01ea-28e0-48e7-85a0-ba6caec3fcea?version=1.2 |
| work_keys_str_mv | AT martinmatejka theusageofstatespacemodelsinmortalitymodelingandpredictions AT ivanamala theusageofstatespacemodelsinmortalitymodelingandpredictions AT martinmatejka usageofstatespacemodelsinmortalitymodelingandpredictions AT ivanamala usageofstatespacemodelsinmortalitymodelingandpredictions |