TY  - JOUR
AU  - Tuljapurkar,Shripad
AU  - Edwards,Ryan D.
TI  - Variance in Death and Its Implications for Modeling and Forecasting Mortality
JF  - National Bureau of Economic Research Working Paper Series
VL  - No. 15288
PY  - 2009
Y2  - August 2009
UR  - http://www.nber.org/papers/w15288
L1  - http://www.nber.org/papers/w15288.pdf
N1  - Author contact info:
Shripad Tuljapurkar
Stanford University
Center on Longevity
Herrin Labs, Room 454
Stanford, CA 94305
Tel: 650/724-4171
E-Mail: tulja@stanford.edu

Ryan D. Edwards
Department of Economics
Queens College, CUNY
Powdermaker Hall 300-S
Flushing, NY 11367
Tel: 718/997-5189
Fax: 718/997-5466
E-Mail: redwards@qc.cuny.edu
AB  - Entropy, or the gradual decline through age in the survivorship function, reflects the considerable amount of variance in length of life found in any human population. Part is due to the well-known variation in life expectancy between groups: large differences according to race, sex, socioeconomic status, or other covariates. But within-group variance is very large even in narrowly defined groups, and it varies strongly and inversely with the group average length of life. We show that variance in length of life is inversely related to the Gompertz slope of log mortality through age, and we reveal its relationship to variance in a multiplicative frailty index. Our findings bear a variety of implications for modeling and forecasting mortality. In particular, we examine how the assumption of proportional hazards fails to account adequately for differences in subgroup variance, and we discuss how several common forecasting models treat the variance along the temporal dimension.
ER  -