Open AccessData granularity in mid-year life table construction
Author(s) -
José M. Pavía,
Natàlia Salazar,
Josep Lledó
Publication year - 2020
Language(s) - English
Resource type - Conference proceedings
DOI - 10.4995/carma2020.2020.11611
Subject(s) - table (database) , estimator , population , statistics , period (music) , computer science , construct (python library) , granularity , sample (material) , life insurance , product (mathematics) , econometrics , demography , actuarial science , mathematics , data mining , economics , sociology , physics , chemistry , geometry , chromatography , acoustics , programming language , operating system
Life tables have a substantial influence on both public pension systems andlife insurance policies. National statistical agencies construct life tables fromhypotheses death rate estimates to the (mx aggregated ), or death figures probabilities of demographic (q x ), after applying events (deaths, variousmigrations and births). The use of big data has become extensive acrossmany disciplines, including population statistics. We take advantage of thisfact to create new (more unrestricted) mortality estimators within the familyof period-based estimators, in particular, when the exposed-to-riskpopulation is computed through mid-year population estimates. We useactual data of the Spanish population to explore, by exploiting the detailedmicrodata of births, deaths and migrations (in total, more than 186 milliondemographic events), the effects that different assumptions have oncalculating death probabilities. We also analyse their impact on a sample ofinsurance product. Our results reveal the need to include granular data,including the exact birthdate of each person, when computing period mid-year life tables.