The loop of research software development
How developing statistical software for multilevel regression and poststratification helped us to develop clarity on the methods
Presented by Dr Lauren Kennedy (Monash University)
Multilevel regression and poststratification (MRP) has become increasingly popular as a method for adjusting non-representative samples to make wider population based estimates.
It has been demonstrated to be particularly effective in small area estimation and non-probability samples. However, practical implementation can be quite messy to implement in research code. To rectify this, we developed an R package to assist users with the practical implementation of MRP.
In doing so we gained greater clarity of the implicit process of conducting an MRP analysis, which has helped us to generate research questions and a deeper understanding of the method. In this seminar I will provide an overview of MRP and when it is used, an overview of our software and finish with an overview of what we learnt.
Speaker
Lauren Kennedy is a lecturer in Business Analytics at Monash University Econometrics and Business Statistics department.
Before joining Monash she worked at Columbia University on the Poverty Tracker and Fragile Families Surveys. She completed her PhD in psychology in 2018 at the University of Adelaide, where she focussed on assumptions of statistical methods used in psychology.
Register now
As part of the Centre of Health Economics' vibrant research culture, we host a weekly seminar series where visiting and invited researchers present current research relating to the economics of health and wellbeing, and the healthcare sector. Visitors are welcome to join these sessions where discussion and debate is encouraged.
Contact shannon.stanwell@monash.edu for registration details.
Event Details
- Date:
- 13 October 2021 at 12:00 pm – 1:00 pm
- Venue:
- Online
- Categories:
- Health Economics; CHE Seminar
Description
How developing statistical software for multilevel regression and poststratification helped us to develop clarity on the methods
Presented by Dr Lauren Kennedy (Monash University)
Multilevel regression and poststratification (MRP) has become increasingly popular as a method for adjusting non-representative samples to make wider population based estimates.
It has been demonstrated to be particularly effective in small area estimation and non-probability samples. However, practical implementation can be quite messy to implement in research code. To rectify this, we developed an R package to assist users with the practical implementation of MRP.
In doing so we gained greater clarity of the implicit process of conducting an MRP analysis, which has helped us to generate research questions and a deeper understanding of the method. In this seminar I will provide an overview of MRP and when it is used, an overview of our software and finish with an overview of what we learnt.
Speaker
Lauren Kennedy is a lecturer in Business Analytics at Monash University Econometrics and Business Statistics department.
Before joining Monash she worked at Columbia University on the Poverty Tracker and Fragile Families Surveys. She completed her PhD in psychology in 2018 at the University of Adelaide, where she focussed on assumptions of statistical methods used in psychology.
Register now
As part of the Centre of Health Economics' vibrant research culture, we host a weekly seminar series where visiting and invited researchers present current research relating to the economics of health and wellbeing, and the healthcare sector. Visitors are welcome to join these sessions where discussion and debate is encouraged.
Contact shannon.stanwell@monash.edu for registration details.