City Research Online

Abstract

We introduce a model-agnostic procedure to construct prediction intervals for the age distribution of deaths. The age distribution of deaths is an example of constrained data, which are nonnegative and have a constrained integral. A centered log-ratio transformation and a cumulative distribution function transformation are used to remove the two constraints, where the latter transformation can also handle the presence of zero counts. Our general procedure divides data samples into training, validation, and testing sets. Within the validation set, we can select an optimal tuning parameter by calibrating the empirical coverage probabilities to be close to their nominal ones. With the selected optimal tuning parameter, we then construct the pointwise prediction intervals using the same models for the holdout data in the testing set. Using Japanese age- and sex-specific life-table death counts, we assess and evaluate the interval forecast accuracy with a suite of functional time-series models.

Publication Type:	Article
Additional Information:	This is an Accepted Manuscript of an article to be published by Taylor & Francis in Scandinavian Actuarial Journal, available at: www.tandfonline.com/journals/SACT
Publisher Keywords:	compositional data analysis, functional principal component analysis, functional time series, prediction interval calibration, split conformal prediction, standard deviation-based conformity
Subjects:	H Social Sciences > HA Statistics
Departments:	Bayes Business School Bayes Business School > Faculty of Actuarial Science & Insurance
SWORD Depositor:	Symplectic Administrator

Export

Downloads