Speaker: Kristoffer Herland Hellton, Senior Research Scientist at the Norwegian Computing Center
Title: Significance for a modern world
Abstract: At this year’s Joint Statistical Meeting, Emmanuel Candes (Stanford) introduced an entirely new framework for assessing significance, regardless of method, while provably controlling the false discovery rate. The key idea is to make up fake variables, so-called “knockoffs”, which are created from the knowledge of the predictors alone, requiring no new data or knowledge of the response variable. For nearly a century, science has operated by empirically testing theories, but now Candes states: ''we have entered a new world where large data sets are available prior to the formulation of scientific theories. Researchers mine these data relentlessly and we have run into the problem of irreproducibility. The field of Statistics needs to re-invent itself to adapt to the new reality...''. This talk will present the highlights of Candes' Wald lectures and the new framework of knockoffs.
The lunch starts at 12:00, and the talk will start around 12:20.
NB: Wednesday BigInsight Lunches are open to staff and students from any of the BigInsight partners, including UiO, but not to others.
Location: Spiseriet, Norwegian Computing Center