Please join us in person or online for our September Queensland Branch Meeting. The seminar will start at 5:00 pm. Details for the seminar are provided below.
TITLE: Almost all log-scale output is readily interpretable
SPEAKER: Mark Chatfield, University of Queensland
TIME: 5:00 - 6:30 pm (AEST), 18st September 2024
VENUE: 223 Teaching Suite, UQ Brisbane City, 308 Queen St, Brisbane and online (Zoom details will be sent with registration).
Special instructions for in-person venue:
Enter through the main door at 308 Queen Street and pass through the Atrium. Speak to the concierge at the elevator located at the back of the room, and notify them that you are attending the Statistical Society of Australia event.
Please note that the seminar will be recorded and might be put on YouTube or similar platform.
ABSTRACT:
As statisticians, we frequently come across log-scale output when modelling binary, count, time-to-event and skewed continuous data. While log-scale regression coefficients, SDs, SEs, bias and RMSE can be exponentiated and interpreted, this is often not the only way. Building on the work of others, I will explain how almost all loge-scale output is readily interpretable, without exponentiating. As well as seeing meaning in log-scale output, such knowledge provides more tools in the statistician’s toolbox. I will show this for the analysis of log-transformed data, the Cox model, random-effects meta-analysis of risk ratios, and the performance of odds ratio estimators.
SPEAKER'S BIO:
Mark Chatfield is a senior statistician at The University of Queensland Clinical Trials Centre. Since studying maths (BA, Oxford) and statistics (MSc, Southampton), he has worked as a statistician in health and medical research institutes and universities for 22 years. He is undertaking a PhD on tonight’s topic.
@StatSocAus
