We are pleased to announce that Daniela Witten, Professor of Statistics and Biostatistics and Dorothy Gilford Endowed Chair, has received grant funding support from the Office of Naval Research (ONR) for her research on “Inference After Unsupervised Learning”.
This proposal involves developing valid methods for statistical inference in the presence of double-dipping, which arises when researchers generate and then test a hypothesis on the same data. This practice is problematic because for a classical hypothesis test to be valid, the hypothesis must be specified before looking at the data. By violating this principle, double-dipping leads to spurious results, e.g. in the form of vastly inflated Type 1 errors, and confidence intervals that fail to attain the nominal coverage. Double-dipping affects data analyses across virtually all areas of application. It is especially problematic when the hypothesis tested is generated using an unsupervised learning approach, since in that setting, sample splitting --- natural solution to overcome double dipping in many settings --- is often not applicable.
Congratulations to Daniela Witten on her success!