A comparative assessment of univariate longevity measures using zoological animal records

Abstract

Comparative biogerontology evaluates cellular, molecular, physiological, and genomic properties that distinguish short-lived from long-lived species. These studies typically use maximum reported lifespan (MRLS) as the index with which to compare traits, but there is a general awareness that MRLS is not ideal owing to statistical shortcomings that include bias resulting from small sample sizes. Nevertheless, MRLS has enough species-specific information to show strong associations with many other species-specific traits, such as body mass, stress resistance, and codon usage. The major goal of this study was to see if we could identify surrogate measures with better statistical properties than MRLS but that still capture inter-species differences in extreme lifespan. Using zoological records of 181 bird and mammal species, we evaluated 16 univariate metrics of aging and longevity, including nonparametric quantile-based measures and parameters derived from demographic models of aging, for three desirable statistical properties. We wished to identify those measures that: (i) correlated well with MRLS when the biasing effects of sample size were removed; (ii) correlated weakly with population size; and (iii) were highly robust to the effects of sampling error. Nonparametric univariate descriptors of the distribution of lifespans clearly outperformed the measures derived from demographic analyses. Mean adult lifespan and quantile-based measures, and in particular the 90th quantile of longevity, performed particularly well, demonstrating far less sensitivity to small sample size effects than MRLS while preserving much of the information contained in the maximum lifespan measure. These measures should take the place of MRLS in comparative studies of lifespan.

Figure 1. Two methods of determining age of onset

shows the joint distribution between 1) the oldest of the two sex-specific values for the first age of reproduction and 2) age at minimal mortality for 163 species with 50 or more adults (as defined by both definitions). The line defines the T₂ = T₁ relationship.

Figure 2. Correlations between longevity metrics and population size

illustrates the correlations between candidate metrics and population size. Correlations are sensitive to the definition of adult (T) used to estimate the measures. For each measure, bars connect the T₁ and T₂-derived estimates. Long bars indicate high sensitivity of the correlation to the choice of T.