SSA SOUTH AUSTRALIAN BRANCH – 22 August MEETING
The South Australian Branch of the Statistical Society would like to invite you to the August meeting of the 2018 program.
Venue: Napier Building, Room-144, North Terrace, Adelaide University. Campus map is available at http://www.adelaide.edu.au/campuses/northtce/.
***Please note that most entrance doors to Adelaide University buildings close at 6pm so make sure you arrive in time for the talk.
5.30pm – Refreshments in the Lecture Theatre.
6.05pm – General Meeting Talk.
7.30 pm – A dinner will be held after the meeting at Lemongrass Thai Bistro, 289 Rundle St, Adelaide SA 5000.
Please rsvp for dinner to [email protected]sahmri.com by 20th Aug as we are usually unable to change the booking numbers at the last minute.
Speaker: Andrew Vincent
Topic: Early-stopping adaptive trial designs: Bayesian or frequentist?
Andrew Vincent has a degree in Mathematics and Statistics here at the University of Adelaide, a PhD in applied mathematics from the University of Sydney. In 2005 he joined the Netherlands Cancer Institute’s clinical trials department as a biostatistician, primarily working on the design and analysis of investigator-led cancer drug trials. In 2013 he returned to Adelaide to join the University of Adelaide’s Freemason’s Foundation Men’s Health Centre as their in-house statistical consultant. Currently he supports a diverse range of medical projects including prostate cancer, obesity, diet, depression, schizophrenia and sleep apnoea.
Abstract: Currently in medical research randomized controlled trials (RCT) are the gold standard for inferring causal effect; ideally double-blinded, with experimental vs standard of care as the comparison, and predominantly under the frequentist paradigm. Certainly in the confirmatory setting a sufficiently powered frequentist RCT design is appropriate. However for discovery trials, which constitute the majority of medical science, the use of the minimal clinically relevant difference results in sample sizes often far in excess of what is feasible or appropriate for a single-centre early-phase study. In the area of drug development adaptive randomized Phase II studies, both frequentist and Bayesian are now considered standard. However in medical research in general there is limited use of these designs. Early stopping adaptive designs are likely to have much lower (expected) sample sizes, which is ideal in the early-stage discovery RCT setting. Today I discuss logistical issues associated with these simple adaptive designs, and contrast properties of the standard Frequentist and Bayesian designs.
Feel free to forward this meeting notice to colleagues, all welcome.
Statistical Society of Australia
Phone: 08 8128 4754
|Time:||5:30 pm - 7:15 pm|
|Location:||Napier Building, Room-144,