Centre for Health and Social Analytics (CHSA) is led by Professor Alberto Nettel-Aguirre, it contributes to the University’s Health and Wellbeing Strategy and the Data and Decision Science Framework.
Centre for Health and Social Analytics
The CHSA is being established as a centre within the National Institute for Applied Statistics Research Australia (NIASRA) with the aim of significantly increasing the University's capacity, capabilities, focus and performance in health, medical and social research. CHSA will have a focus on the acquisition, management, analysis, dissemination and interpretation of large and complex data sets. CHSA’s director has expertise in and focus on the use of Biostatistics and Data Science in health research.
CHSA’s portfolio will cover highly collaborative enterprises and projects in health research aligning with UOW’s health and wellbeing strategy; including development of modern biostatistical/data science methods and capacity building short courses.
The aim of CHSA is to ensure that correct use of Biostatistical and data science methods in health research, while making substantial contributions to all steps of health research methods, including data collection, measurement and analysis with a focus on translation.
Major research projects
- CHild Active-transportation Safety and the Environment (CHASE)
- CHILDNEPH- A national (Canadian) initiative to improve care and outcomes for patients with nephrotic syndrome.
- SMIHS Research Advisory Group (UOW)
- Analysis of health promotion research teams employed by NSW Health, and Social networks of school-aged children in Canada (UOW-USydney)
- Long-term effects of musculoskeletal injuries using CHRISP data (UOW)
- Ethics, Legal and Social Implications Project – General Practice Data (UOW)
- Outlining identity problems in the regulation of adaptive changes in AI, (UOW-Macquarie U)
- Anti microbial resistance (UOW)
- Introduction to Mixed Modelling
- Introduction to Data Science & Machine Learning for Health and Social Sciences workshop
Mixed modelling is central to modern statistical analysis and is often considered the go-to analysis for large health, social science, ecological, and biological data sets, particularly when there are repeated measurements for each subject or when there is clustering or multiple-levels apparent in the data. Mixed models can also be applied to longitudinal data with missing observations, a common hinderance to fitting ANOVA models. Able to be used across many data situations, mixed models are a form of regression analysis that are essential for any pioneering data analyst to have available to them.
This introductory in-person workshop covers the basics of building linear statistical models, covering standard regression analysis, interpreting categorical predictors and using interaction terms. We introduce exactly what are mixed models, what data is suited to mixed models, how to apply mixed models in R, and how to properly interpret the results. We will also cover the basics of using R and RStudio and give an overview of the tidyverse functions that can help get your data in the correct form for analysis. No prior knowledge of R is necessary. We will also show you how to create appealing data visualisations for clustered data using ggplot2.
This is a unique entry level workshop specifically designed to teach the basics of data science and machine learning for the health and social sciences.
The workshop will cover the most in demand data science and machine learning methods for both supervised (regression, classification and regression trees, neural nets and support vector machines) and unsupervised learning (clustering). Participants will learn how to choose the appropriate method, and how to analyse and interpret the results using RStudio. No prior knowledge of RStudio is necessary, RStudio will be introduced as part of the course.
Professor Marijka Batterham, Professor Alberto Nettel-Aguirre, and Dr Brad Wakefield from the Statistical Consulting Centre and the Centre for Health and Social Analytics
Contact: email@example.com for additional course information