His own recent work, on the ability to spot false discoveries, is aimed at the genetics problem.
With huge data sets and fine-grained measurement, statisticians and computer scientists note, there is increased risk of "false discoveries".
The study, "False Discoveries in Mutual Fund Performance: Measuring Luck in Estimating Alphas," has been circulating for over a year in academic circles.
As discussed, this redundancy of data can alter statistical analysis and lead to greater numbers of false discoveries.
On Saturday afternoon, I attended the symposium entitled: "False Discoveries and Statistics: Implications for Health and the Environment".
The application of high-throughput procedures to the discovery of biomarkers leads to large datasets of multi-dimensional data and a certain percentage of false discoveries.
While these factors certainly contribute to irreproducibility, relatively little attention outside of the specialized statistical literature has focused on the expected prevalence of false discoveries under idealized circumstances.
Though probability of detection is a good performance measure, in many applications controlling the false discoveries below a desired level is more crucial.
This ion-centric approach leads to a greater number of false discoveries as a result of increased numbers of measurements processed in the statistical analysis.
Scientists tried to find it in nature; given its rarity, these attempts resulted in several false discoveries.
Statisticians are essential to realizing the promise of this age of Big Data, ensuring that sound decisions are made and mitigating the threat of false discoveries.
