A two-component regression model for the number of births

Thursday, 22 September 2016
AMREP Education Centre, Alfred Hospital, Ground Floor, Classroom 2
55 Commercial Rd
Prahran 3004

The number of births (parity) clearly bears a relationship to a woman’s age.  A negative binomial regression model for parity is developed, in which mean parity is modelled with two components relating to age. The first is a parametric growth curve which operates during the childbearing years. The second is a cohort effect which models changes in birth rates over time, and is a nonparametric term. The model is implemented on Fijian and US data, and provides insight into different trends in childbearing.

Professor Gillian Heller

Prof. Gillian Heller

Department of Statistics
Macquarie University, Sydney

Gillian Heller is Professor of Statistics at Macquarie University, Sydney. Her research interests are in flexible regression modelling, with applications in biostatistics and insurance. She has done statistical work at a women’s health centre in Fiji, which motivated the topic of this talk.

PDF icon Heller_talk_Melbourne_2016.pdf889.28 KB