Estimating stature in fossil hominids: which regression model and reference sample to use?

Researchers have long appreciated the significant relationship between body size and an animal's overall adaptive strategy and life history. However, much more emphasis has been placed on interpreting body size than on the ac tual calculation of it. One measure of size that is especially important fo r human evolutionary studies is stature. Despite a long history of investig ation, stature estimation remains plagued by two methodological problems: ( 1) the choice of the statistical estimator, and (2) the choice of the refer ence population from which to derive the parameters. This work addresses both of these problems in estimating stature for fossil hominids, with special reference to A.L. 288-1 (Australopithecus afarensis ) and WT 15000 (Homo erectus). Three reference samples of known stature wit h maximum humerus and femur lengths are used in this study: a large (n=2209 ) human sample from North America, a smaller sample of modem human pygmies (n=19) from Africa, and a sample of wild-collected African great apes (n=85 ). Five regression techniques are used to estimate stature in the fossil ho minids using both univariate and multivariate parameters derived from the r eference samples: classical calibration, inverse calibration, major axis, r educed major axis and the zero-intercept ratio model. We also explore a new diagnostic to test extrapolation and allometric differences with multivari ate data, and we calculate 95% confidence intervals to examine the range of variation in estimates for A.L. 288-1, WT 15000 and the new Bouri hominid (Australopithecus garhi). Results frequently vary depending on whether the data are univariate or mul tivariate. Unique limb proportions and fragmented remains complicate the ch oice of estimator. We are usually left in the end with the classical calibr ator as the best choice. It is the maximum likelihood estimator that perfor ms best overall, especially in scenarios where extrapolation occurs away fr om the mean of the reference sample. The new diagnostic appears to be a qui ck and efficient way to determine at the outset whether extrapolation exist s in size and/or shape of the long bones between the reference sample and t he target specimen. (C) 2000 Academic Press.