CMI Afternoon Seminar: Grouped functional time series forecasting method for multiple sub-populations
|Starts:||15:00 29 May 2018|
|Ends:||16:30 29 May 2018|
|What is it:||Seminar|
|Organiser:||School of Social Sciences|
|Who is it for:||University staff, Adults, Alumni, Current University students, General public|
|Speaker:||Associate Professor Han Lin Shang|
Associate Professor Han Lin Shang, Associate Professor of Statistics, Australian National University
Abstract: Age-specific mortality rates are often disaggregated by different attributes, such as sex, state,
ethnic group, education and socioeconomic status. Forecasting age-specific mortality rates at the
national and sub-national levels play a vital role in developing social policy and pricing annuity.
However, the independent mortality forecasts at the sub-national levels may not add up to the
forecasts at the national level. Further, the independent forecasts may not utilize correlation
among sub-populations to improve forecast accuracy. To address these two issues, we modify
and extend the grouped univariate functional time series to grouped multivariate functional time
series forecasting. For quantifying forecast uncertainty, we utilize a nonparametric bootstrap
method to reconcile interval forecasts. Using the regional age-specific mortality rates in Japan
obtained from the Japanese Mortality Database (2018), we investigate the one-step-ahead to 15-
step-ahead forecast accuracy among the independent and grouped univariate and multivariate
functional time series forecasting methods. The grouped multivariate functional time series
forecasting methods are not only shown to be useful for reconciling forecasts of age-specific
mortality rates at national and sub-national levels, but they also use multivariate functional
principal component regression to jointly model sub-populations and enjoy potentially improved
forecast accuracy averaged over different disaggregation factors. The improved forecast accuracy
of mortality rates is of great interest to the insurance and pension industries for estimating
annuity prices, in particular at the level of population sub-groups, defined by critical factors
such as sex, region, and socioeconomic grouping.
Tea/coffee and cakes from 2.45.
Join us for this event, which is part of the CMI Afternoon Seminar Series. All welcome. No registration necessary.
The Cathie Marsh Institute for Social Research (CMI) provides a focal point at The University of Manchester for the application of quantitative methods in interdisciplinary social science research in order to generate a world class research environment.
Associate Professor Han Lin Shang
Role: Associate Professor of Statistics
Organisation: Australian National University
Travel and Contact Information
CMI Seminar Room, 2.07
Humanities Bridgeford Street