| Home | Research | Teaching | Vitae | Presentations | Resources | Contact |
| My current research interest is the large-scale multiple hypothesis testing for high dimensional (HD) data. HD data sets are increasingly popular as high-throughput technology such as imaging and RNA/DNA sequencing software are routinely utilized to generate data that allows for thousands or millions of null hypotheses to be tested with a relatively small number of experimental units. The challenge here is that multiplicity corrections must be made to safeguard against a high false positive rate, but standard methods are designed for independent and identically distributed test statistics with continuous distributions when in fact test statistics are not independent and often have discrete and heterogenous distributions. I have recently become interested in publication policies for addressing false positive rates among published results in social, behavioral, biomedical and other sciences that rely on hypotheses testing for discovery. |