Inverse prediction for multivariate mixed models with standard software
Inverse prediction (IP) is reputed to be computationally inconvenient for multivariate responses. This paper describes how IP can be formulated in terms of a general linear mixed model, along with a flexible modeling approach for both mean vectors and variance–covariance matrices. It illustrates that results can be had as standard output from widely-available statistical computing packages.
KeywordsHeteroscedastic multivariate models Multivariate calibration Forensic entomology
Mathematics Subject Classification62H15 62J05 62H30
- Catts EP (1992) Problems in estimating the postmortem interval in death dnvestigations. J Agric Entomol 9(4):245–255Google Scholar
- LaMotte, LR, and Wells JD (2016). Inverse prediction for heteroscedastic response using mixed models software. Commun Stat Simul Comput. (Published online 21 Nov 2015)Google Scholar
- SAS Institute Inc. (2012) SAS 9.4. Cary NC, USAGoogle Scholar
- Wells JD, LaMotte LR (1995) Estimating maggot age from weight using inverse prediction. J Forensic Sci JFSCA 40(4):585–590Google Scholar