Abstract
This chapter presents methodological principles of a new fully Bayesian method, based on a precise statistical model taking into consideration the uncertainty of all the data upon which the estimation is based, in order to solve this major and recurrent problem for palaeodemographers. The main advantages of this approach over the previous ones are discussed, and palaeodemographers are encouraged to propose further insights that may be necessary to extend this approach.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
The IALK method can be modified to take account of this randomness. One proposal is given in Box 13.2 (see p. 273); while this does improve the method in some ways, it may weaken it in others, which confirms our view that more radical changes in viewpoint are necessary.
- 2.
This is true of Bocquet-Appel and Bacro’s method (2008), which takes account of the nature of the probabilities to be estimated by reducing the parametric space of the standard framework.
- 3.
One example is the set of data processed in Sect. 13.4. But there are cases where this approximation is highly unsatisfactory: an example of a bimodal posterior distribution is even given in Séguy et al. (2012).
- 4.
A study of this site with five suture stages instead of seven and 5-year age classes (a total of 13) has been carried out and is given in Séguy et al. (2012). The results tally completely, showing in particular that the method described here works effectively with significantly more age classes than stages.
- 5.
Note, however, that with the reference probabilities we are using, the sample is fully compatible with the documented values. If we calculate theoretical frequencies for stages from these data and compare them with the observed values by chi-squared test, we obtain 1.93 with 6 degrees of freedom.
References
Bocquet-Appel, J.-P., & Bacro, J.-N. (2008). Estimation of an age distribution with its confidence intervals using an iterative Bayesian procedure and a bootstrap sampling approach. In J.-P. Bocquet-Appel (Ed.), Recent advances in palaeodemography. Data, techniques, patterns (pp. 63–82). Dordrecht: Springer Verlag.
Caussinus, H., & Courgeau, D. (2010). Estimating age without measuring it: A new method in palaeodemography. Population English edition, 65(1), 117–144.
R Development Core Team. (2008). R: A language and environment for statistical computing, R foundation for statistical computing. Vienna, Austria. URL http://www.R-project.org
Robert, P. (2006). Le choix bayésien. Principes et pratique (Statistique et probabilités appliquées). Paris: Springer-Verlag-France.
Séguy, I., Caussinus, H., Courgeau, D., Buchet, L. (2013). Estimating the age structure of a buried adult population: a new statistical approach applied to archaeological digs in France. American Journal of Physical Anthropology, 150 (2), 170-183
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Caussinus, H., Courgeau, D. (2013). A New Method for Estimating Age-at-Death Structure. In: Handbook of Palaeodemography. INED Population Studies, vol 2. Springer, Cham. https://doi.org/10.1007/978-3-319-01553-8_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-01553-8_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-01552-1
Online ISBN: 978-3-319-01553-8
eBook Packages: Humanities, Social Sciences and LawSocial Sciences (R0)