Logistic Regression (DSCRP) [webinar]

This is a DSCRP course and places are limited. If you are unable to attend, please de-register (or email graduateschool@uq.edu.au if you are unable to do so). An unexplained absence could result in all your future DSCRP registrations becoming Waitlisted. You may only attend the workshop once. Repeat bookings will be removed and placed on the Waitlist.

This hands-on workshop introduces participants to logistic regression, a statistical technique used to model binary outcomes such as yes or no decisions from complex datasets. The session blends theoretical understanding with practical exercises in R, focusing on how logistic regression can be applied for both inference and prediction. 

Who Should Attend 

This workshop is ideal for researchers and HDR students working with binary outcome data who want to improve their analytical skills. While the content is applicable across disciplines, examples and exercises will primarily draw from biological datasets. 

Prerequisites 

Participants should have prior experience with R and the command line interface, equivalent to the level covered in our previous R workshop. A foundational understanding of statistical hypothesis testing and regression analysis is also expected, as basic R concepts will not be revisited. 

Learning Outcomes 

By the end of the workshop, participants will be able to: 

• Understand the analysis of categorical variables 
• Grasp the principles behind logistic regression 
• Perform both univariate and multivariate logistic regression in R 
• Evaluate the fit and performance of logistic regression models 
• Recognise common pitfalls and limitations in logistic regression analysis 

 Workshop Topics 

• Identifying datasets suitable for logistic regression and framing relevant research questions 
• Understanding the theoretical foundations of logistic regression 
• Conducting logistic regression analyses using R 
• Interpreting and critically assessing output from logistic regression models in R