Person:
Cefalu, Matthew Steven

Profile Picture

Email Address

AA Acceptance Date

Birth Date

Research Projects

Organizational Units

Job Title

Last Name

Cefalu

First Name

Matthew Steven

Name

Cefalu, Matthew Steven
Author's Publications: search.filters.isAuthorOfPublication.d6f82071-5491-4c0c-9730-7b30ff10922e

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    Completing the Results of the 2013 Boston Marathon
    (Public Library of Science, 2014) Hammerling, Dorit; Cefalu, Matthew Steven; Cisewski, Jessi; Dominici, Francesca; Parmigiani, Giovanni; Paulson, Charles; Smith, Richard L.
    The 2013 Boston marathon was disrupted by two bombs placed near the finish line. The bombs resulted in three deaths and several hundred injuries. Of lesser concern, in the immediate aftermath, was the fact that nearly 6,000 runners failed to finish the race. We were approached by the marathon's organizers, the Boston Athletic Association (BAA), and asked to recommend a procedure for projecting finish times for the runners who could not complete the race. With assistance from the BAA, we created a dataset consisting of all the runners in the 2013 race who reached the halfway point but failed to finish, as well as all runners from the 2010 and 2011 Boston marathons. The data consist of split times from each of the 5 km sections of the course, as well as the final 2.2 km (from 40 km to the finish). The statistical objective is to predict the missing split times for the runners who failed to finish in 2013. We set this problem in the context of the matrix completion problem, examples of which include imputing missing data in DNA microarray experiments, and the Netflix prize problem. We propose five prediction methods and create a validation dataset to measure their performance by mean squared error and other measures. The best method used local regression based on a K-nearest-neighbors algorithm (KNN method), though several other methods produced results of similar quality. We show how the results were used to create projected times for the 2013 runners and discuss potential for future application of the same methodology. We present the whole project as an example of reproducible research, in that we are able to make the full data and all the algorithms we have used publicly available, which may facilitate future research extending the methods or proposing completely different approaches.
  • Thumbnail Image
    Publication
    Statistical Methods for Effect Estimation in Biomedical Research: Robustness and Efficiency
    (2013-09-30) Cefalu, Matthew Steven; Dominici, Francesca; Parmigiani, Giovanni; Tchetgen Tchetgen, Eric
    Practical application of statistics in biomedical research is predicated on the notion that one can readily return valid effect estimates of the health consequences of treatments (exposures) that are being studied. The goal as statisticians should be to provide results that are scientifically useful, to use the available data as efficiently as possible, to avoid unnecessary assumptions, and, if necessary, develop methods that are robust to incorrect assumptions. In this dissertation, I provide methods for effect estimation that meet these goals. I consider three scenarios: (1) clustered binary outcomes; (2) continuous outcomes with a binary treatment; and (3) continuous outcomes with potentially missing continuous exposure. In each of these settings, I discuss the shortfalls of current statistical methods for effect estimation available in the literature and propose new and innovative methods that meet the previously stated goals. The validity of each proposed estimator is theoretically verified using asymptotic arguments, and the finite sample behavior is studied through simulation.