series event

We need better tools to solve these problems - a (friendly) introduction to several new statistical techniques to improve your research

Mike Baiocchi will deliver this talk entitled 'We need better tools to solve these problems - a (friendly) introduction to several new statistical techniques to improve your research'.

Our team's research on prevention of sexual assault in Kenya has led to the development of several new statistical techniques to overcome challenges inherent in contexts where behaviours and specifically behaviour-change are of great importance. Time will not permit discussion of each technique, so a quick survey of the audience, and what you all are interested in, will determine which techniques we focus on. The techniques include: (i) a method for designing randomised trials when you anticipate "spillover" or "contamination" between the intervention groups, (ii) a method for using open-response/free-text and getting "confidence sets" and "p-values" that rigorously assess the causal differences between the two groups, (iii) a simplified approach to analysing intermediate effects between an intervention and an outcome (this approach stands in contrast to the structural equation models approach), (iv) a means for adaptively "fixing" measurement error in a large data set so as to avoid biases, and (v) the most technical: a method of inference for cluster-randomised trials that can account for imbalances due to unmeasured baseline confounders (i.e., a nonparametric sensitivity model). NOTE: While the presenter loves statistics very much, he understands that this may not be the case for the general audience. The goal of this talk is to present cool new methods that are useful for you and your research. Lots of intuition and pictures will be used.

Michael Baiocchi, PhD, is an Assistant Professor in the Stanford Prevention Research Center, at Stanford University He is an interventional-statistician, creating interventions and the means for analysing them. He specialises in creating simple, easy to understand statistical methodologies for getting reliable results out of messy data and messy situations. His research is in non-parametric estimation and design-based inference. He was the inaugural Stein Fellow in the department of Statistics at Stanford University. He is the principal investigator on a large (enrollment: 5,000+ students, 100+ schools) randomized study of a sexual assault prevention intervention in the settlements around Nairobi, Kenya. That research is funded by the UK’s Department for International Development as part of its "What Works to Prevent Violence Against Women and Girls" program. In this line of research, he is both lead statistician and lead researcher, acting as the generator of the studies and the developer of the theoretical models.