Stature estimation and calibration: Bayesian and maximum likelihood perspectives in physical anthropology

Many applied problems in physical anthropology involve estimation of an uno bservable quantity (such as age at death or stature) from quantities that a re observable. Two of the more disparate subdisciplines of our discipline, paleoanthropology and forensic anthropology, routinely make use of various estimation methods on a case-by-case basis. We discuss the rationales for m aking estimations on isolated cases, taking stature estimation from femoral and humerus lengths as an example. We show that the entirety of our discus sion can be placed within the context of calibration problems, where a larg e calibration sample is used to estimate an unobservable quantity for a sin gle skeleton. Taking a calibration approach to the problem highlights the e ssentially Bayesian versus maximum likelihood nature of the question of sta ture estimation. On the basis of both theoretical arguments and practical e xamples, we show that inverse calibration (regression of stature on bone le ngth) is generally preferred when the stature distribution for a reference sample forms a reasonable prior, while classical calibration (regression of bone length on stature followed by solving for stature) is preferred when there is reason to suspect that the estimated stature will be an extrapolat ion beyond the useful limits of the reference sample statures. The choice b etween these two approaches amounts to the decision to use either a Bayesia n or a maximum likelihood method. Yrbk Phys Anthropol 41:65-92, 1998. (C) 1 998 Wiley-Liss, Inc.