Brent A. Johnson, PhD
Associate Professor

My methodological research focuses primarily on semiparametric regression in missing data problems, including measurement error, censored data, observational data. Recently, I have developed a taste for machine learning and model selection with a focus on problems that arise in practice. My research has been funded by grants from the National Institute of Health.

I collaborate with a wide variety of investigators in Environmental and Occupational Health, Epidemiology, Medicine, and Genomics. In Occupational Health, the objective of my collaborators is to estimate the functional relationship between benzene exposure and biomarker response and then interpret the resulting curve. The work has public health impact insofar as millions of Americans are exposed to benzene at low levels and the hematopietic risk may not be linear in this low dose range, contrary to what has been believed for many years.

I also collaborate with a number of investigators in HIV/AIDS epidemiology, both in prevention as well as therapeutics. One project attempts to assess whether it is beneficial to stay on a failing antiretroviral regimen rather than switch immediately to second-line regimen. Our results have been submitted for publication. I have also collaborated on a paper from the Rwanda Zambia HIV Research Group where investigators have evaluated the effect of couples counseling. I am also involved with domestic HIV prevention right here in Atlanta where investigators introduced similar couples counseling and testing to what has proven effective in Africa.

I have also worked with experts in cancer genomics and bioinformatics, nutrition, and cardiology. My interest in cancer genomics has been primarily through microarray analyses and their association with clinical outcomes, such as cancer recurrence. My work in cardiology has been through my thesis topic of estimating the expected clinical endpoint for a given infusion dose (measured in hours), when infusion may be stopped for a number of different competing reasons.

In the upper right, a 36" striped bass I caught fly-fishing with my brother-in-law, Matt Hamilton, near Island No. 3, Chesapeake Bay Bridge Tunnel, Virginia Beach, Virgina, USA, in October 2010. This bass was released and lived to see another sun rise over the Atlantic.

In the lower left and right pictures, a 12-lb false albacore caught fly-fishing with my brother-in-law, Matt Hamilton on a snappy day just inside the "hook" near Cape Lookout, Harker's Island, North Carolina, in November 2006. This fish was also released to continue her migration down the Atlantic coastline.

Education:

Postdoctoral Fellow, Biostatistics, The University of North Carolina-Chapel Hill
Ph. D. in Statistics, North Carolina State University
M. S. in Biostatistics, University of Minnesota
B. A. in Mathematics, St. Olaf College

Select Publications: (For a longer list, see Publications)

Li L, Eron J, Ribaudo H, Gulick RM, Johnson BA (2012) Evaluating the effect of early versus late ARV regimen change if failure on an initial regimen: results from the AIDS Clinical Trials Group Study A5095. Journal of the American Statistical Association (In press).

Long Q, Chung M, Moreno C, Johnson BA. (2011) Risk prediction for cancer recurrence through regularized estimation with simultaneous adjustment for nonlinear clinical effects. Annals of Applied Statistics (In press).

Johnson BA, Long Q, Chung M. (2011) On path restoration for censored outcomes. Biometrics (In press).

Johnson BA, Long Q. (2011) Survival ensembles by the sum of pairwise differences. Annals of Applied Statistics (In press).

Johnson BA. (2009) Rank-based estimation in the L1-regularized partly linear model for censored outcomes with application to integrated analyses of clinical predictors and gene expression data. Biostatistics 10, 659-666.

Johnson BA. (2009) On lasso for censored data. Electronic Journal of Statistics, 3, 485-506.

Johnson BA. (2008) Variable selection in semiparametric linear regression with censored data. Journal of the Royal Statistical Society, Series B 70,351-370.

Johnson BA, Lin DY, and Zeng D. (2008) Penalized estimating functions and variable selection in semiparametric regression models. Journal of the American Statistical Association 103,672-680.

Johnson BA and Tsiatis AA. (2005) Semiparametric inference in duration-response studies, where duration may be informatively censored. Biometrika 60,315-323.

Pleil JD, Vette AF, Johnson BA, and Rappaport SM. (2004) Air levels of carcinogenic polycyclic aromatic hydrocarbons after the World Trade Center disaster. Proceedings of the National Academy of Sciences 101,11685-11688

This page created and maintained by Brent A. Johnson. The views and opinions expressed on the page are his own and not necessarily shared by Emory University. Page last updated: February, 2011.