SSA SA Branch September Meeting

The South Australian Branch of the Statistical Society would like to invite you to the September meeting of the 2022 program.

Date: 21 September 2022

Presentation Time: 6:00 – 7:00 pm (Adelaide Time)

Physical Venue: 182 Victoria Square, Flinders University, Adelaide, Boardroom North, Level 11

Virtual Venue: Register here: https://unisa.zoom.us/meeting/register/tZEldeGrpzwvG9GNyZv0LairuIF96cNlL7oM

To adhere with SA Health Covid Safe guidelines and maximum capacity of available facility, please inform us by email to aartigulyani@gmail.com if you are planning to attend the meeting in person.

Schedule:

5.30 pm: Refreshments and networking

6.05 pm: Seminar Presentation

7:30 pm: A dinner will be held for those attending in person. Please RSVP to aartigulyani@gmail.com.

Speaker: Professor Adrian Barnett

Professor Adrian Barnett graduated from University College London with a BSc in Statistics in 1994. After that he worked for SmithKline Beecham and the Medical Research Council as a statistician before coming to Australia to do a PhD. He completed his PhD in Mathematics in 2002. His main interest is how to increase the value of health and medical research.

Topic: Bad Statistics in Medical Research

Abstract: Using the wrong statistical methods can completely invalidate a study's results, potentially wasting years of hard work and misdirecting future research and policy. Despite the importance of statistics, many medical researchers do not have adequate training and/or access to a qualified statistician. Researchers often attempt complex study designs that require advanced statistical knowledge. A common example is diagnostic accuracy studies, but a review of over 200 COVID-19 prediction models found only one of any value with many using statistical methods that were inappropriate and/or badly described. I will make the case for researchers to use simple study designs that only require basic statistical methods. I will discuss the potential for automated statistical reviews to improve research quality.