BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
BEGIN:VEVENT
UID:WILD_APRICOT_EVENT_3816744_SESSION_1
DTSTART:20200422T083000Z
DTEND:20200422T093000Z
SUMMARY:SA Branch Meeting - Dr Murthy Mittinty
LOCATION:virtual Zoom meeting
DESCRIPTION:https://statsoc.org.au/event-3816744\n\nBranch Meeting - Wednesday\, 22nd April 2020\n The South Australian Branch of the Statistical Society would like to invite you to the April meeting of the 2020 program.\n Virtual Venue: Join the Zoom meeting using your PC or device https://adelaide.zoom.us/j/92173108742?pwd=THdtY2FVSTBZMUpaOXVCdnpIQWp6Zz09\n Password: TMLE\n \n or Join from dial-in phone line: Dial: +61 2 8015 2088\n Meeting ID: 921 7310 8742\n\n Speaker: Dr Murthy Mittinty\, The University of Adelaide\n\n Topic: Targeted maximum likelihood estimation for causal inference in observational studies\n\n Abstract\n To attain causal inference from observational studies\, methods such as G-estimation\, Inverse probability treatment weighting\, targeted maximum likelihood estimation (TMLE) are preferred over traditional regression approaches\, which are biased under misspecification of a parametric outcome model. When using\, Inverse probability treatment weighting (IPTW) assumptions such as positivity\, correct specification of exposure model needs to be made. Double robust methods\, which requires correct specification of either exposure or outcome model have been proposed as an improvement over IPTW methods. Targeted maximum likelihood estimation is a semiparametric double‐ robust method that improves the chances of correct model specification by allowing for flexible estimation using (nonparametric) machine‐ learning methods\, super learner. It therefore requires weaker assumptions than its competitors. I provide a step‐ by‐ step guided implementation of TMLE and illustrate it in a realistic scenario based on Dental epidemiology where assumptions about correct model specification and positivity (ie\, when a study participant has 0 probability of receiving the treatment) are nearly violated. This study provides a concise and reproducible educational introduction to TMLE for a binary outcome and exposure. The user should gain sufficient understanding of TMLE from this introductory tutorial to be able to apply the method in practice. \n Biography\n Murthy N Mittinty is a senior lecturer in the School of Public Health at The University of Adelaide. Murthy is interested in both methodological development and applications of statistical methods. His current interests include causal inference\, mediation analysis\, and handling of dynamic treatment regimes. Apart from statistics Murthy has keen interest in history of Mathematics and Statistics and Philosophy. Besides academic interests\, Murthy is interested in Photography and Cooking.\nFeel free to forward this meeting notice to colleagues\, all welcome. \n\n
DTSTAMP:20201031T094349Z
END:VEVENT
END:VCALENDAR