TY - JOUR
T1 - A compositional approach to modeling cause-specific mortality with zero counts
AU - Dong, Zhe Michelle
AU - Shang, Han Lin
AU - Hui, Francis
AU - Bruhn, Aaron
PY - 2025/1/17
Y1 - 2025/1/17
N2 - Understanding and forecasting mortality by cause is an essential branch of actuarial science, with wide-ranging implications for decision-makers in public policy and industry. To accurately capture trends in cause-specific mortality, it is critical to consider dependencies between causes of death and produce forecasts by age and cause coherent with aggregate mortality forecasts. One way to achieve these aims is to model cause-specific deaths using compositional data analysis (CODA), treating the density of deaths by age and cause as a set of dependent, nonnegative values that sum to one. A major drawback of standard CODA methods is the challenge of zero values, which frequently occur in cause-of-death mortality modeling. Thus, we propose using a compositional power transformation, the -transformation, to model cause-specific life-table death counts. The -transformation offers a statistically rigorous approach to handling zero value subgroups in CODA compared to ad hoc techniques: adding an arbitrarily small amount. We illustrate the -transformation in England and Wales and US death counts by cause from the Human Cause-of-Death database, for cardiovascular-related causes of death. The results demonstrate the -transformation improves forecast accuracy of cause-specific life-table death counts compared with log-ratio-based CODA transformations. The forecasts suggest declines in the proportions of deaths from major cardiovascular causes (myocardial infarction and other ischemic heart diseases).
AB - Understanding and forecasting mortality by cause is an essential branch of actuarial science, with wide-ranging implications for decision-makers in public policy and industry. To accurately capture trends in cause-specific mortality, it is critical to consider dependencies between causes of death and produce forecasts by age and cause coherent with aggregate mortality forecasts. One way to achieve these aims is to model cause-specific deaths using compositional data analysis (CODA), treating the density of deaths by age and cause as a set of dependent, nonnegative values that sum to one. A major drawback of standard CODA methods is the challenge of zero values, which frequently occur in cause-of-death mortality modeling. Thus, we propose using a compositional power transformation, the -transformation, to model cause-specific life-table death counts. The -transformation offers a statistically rigorous approach to handling zero value subgroups in CODA compared to ad hoc techniques: adding an arbitrarily small amount. We illustrate the -transformation in England and Wales and US death counts by cause from the Human Cause-of-Death database, for cardiovascular-related causes of death. The results demonstrate the -transformation improves forecast accuracy of cause-specific life-table death counts compared with log-ratio-based CODA transformations. The forecasts suggest declines in the proportions of deaths from major cardiovascular causes (myocardial infarction and other ischemic heart diseases).
KW - Compositional data analysis
KW - alpha transformation
KW - cause of death
KW - log-ratio transformation
KW - mortality forecasting
UR - http://www.scopus.com/inward/record.url?scp=85216394874&partnerID=8YFLogxK
U2 - 10.1017/S1748499524000320
DO - 10.1017/S1748499524000320
M3 - Article
SN - 1748-4995
JO - Annals of Actuarial Science
JF - Annals of Actuarial Science
ER -