TY - JOUR
T1 - Aster models for life history analysis
AU - Geyer, Charles J.
AU - Wagenius, Stuart
AU - Shaw, Ruth G.
PY - 2007/6
Y1 - 2007/6
N2 - We present a new class of statistical models, designed for life history analysis of plants and animals, that allow joint analysis of data on survival and reproduction over multiple years, allow for variables having different probability distributions, and correctly account for the dependence of variables on earlier variables. We illustrate their utility with an analysis of data taken from an experimental study of Echinacea angustifolia sampled from remnant prairie populations in western Minnesota. These models generalize both generalized linear models and survival analysis. The joint distribution is factorized as a product of conditional distributions, each an exponential family with the conditioning variable being the sample size of the conditional distribution. The model may be heterogeneous, each conditional distribution being from a different exponential family. We show that the joint distribution is from a flat exponential family and derive its canonical parameters, Fisher information and other properties. These models are implemented in an R package 'aster' available from the Comprehensive R Archive Network, CRAN.
AB - We present a new class of statistical models, designed for life history analysis of plants and animals, that allow joint analysis of data on survival and reproduction over multiple years, allow for variables having different probability distributions, and correctly account for the dependence of variables on earlier variables. We illustrate their utility with an analysis of data taken from an experimental study of Echinacea angustifolia sampled from remnant prairie populations in western Minnesota. These models generalize both generalized linear models and survival analysis. The joint distribution is factorized as a product of conditional distributions, each an exponential family with the conditioning variable being the sample size of the conditional distribution. The model may be heterogeneous, each conditional distribution being from a different exponential family. We show that the joint distribution is from a flat exponential family and derive its canonical parameters, Fisher information and other properties. These models are implemented in an R package 'aster' available from the Comprehensive R Archive Network, CRAN.
KW - Conditional exponential family
KW - Flat exponential family
KW - Generalized linear model
KW - Graphical model
KW - Maximum likelihood
UR - http://www.scopus.com/inward/record.url?scp=33847409245&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33847409245&partnerID=8YFLogxK
U2 - 10.1093/biomet/asm030
DO - 10.1093/biomet/asm030
M3 - Article
AN - SCOPUS:33847409245
SN - 0006-3444
VL - 94
SP - 415
EP - 426
JO - Biometrika
JF - Biometrika
IS - 2
ER -