Ph.D. (1989) University of Rochester

Michael McDermott Associate Chair Associate Professor of Biostatistics Associate Professor of Neurology     Contact Information: University of Rochester Dept of Biostatistics and Computational Biology 601 Elmwood Avenue Box 630 Rochester, New York 14642   Office: MRBX G-11132 Phone: (585) 275-6685 Fax: (585) 273-1031 E-mail: MikeM@bst.rochester.edu

Research Interests

Much of my statistical research has been in the area of order-restricted inference, specifically with regard to developing novel approaches to hypothesis testing problems involving order-constrained parameters.  This methodology is useful in many applications, including dose-response studies and clinical trials with multiple endpoints.  Recently, I have become interested in problems of inference concerning receiver operating characteristic (ROC) surfaces.  This is a generalization of ROC curve methodology to the situation where subjects or objects may be classified into more than two categories.  I am also currently working on the problem of correcting verification bias that sometimes arises in studies of the performance of diagnostic tests.  Other areas of interest include methods for combining p-values, reliability of measurement, and clinical trials methodology.

I hold a joint appointment with the Department of Neurology, and much of my collaborative work stems from this relationship.  I am a member of several national and international collaborative groups conducting basic and clinical research in Parkinson’s disease, Huntington’s disease, Tourette’s syndrome, epilepsy, periodic paralysis, various muscular dystrophies and other muscle diseases, HIV dementia, multiple sclerosis, and attention deficit-hyperactivity disorder.  I was the primary statistician for the University’s NIH-funded General Clinical Research Center for many years and am now involved in the recently funded Clinical and Translational Sciences Institute.

I was Associate Editor of the journal Neurology from 1997-2003 and I have served on the Medical Advisory Committee of the Muscular Dystrophy Association since 1998.  I was named the Andrew W. Mellon Dean’s Teaching Scholar in 1997 in recognition of excellence in teaching.  I am a member of the American Statistical Association, the Biometric Society, the Institute of Mathematical Statistics, and the Society for Clinical Trials.
 

Selected References

• Mudholkar, G. S. and McDermott, M. P. (1989). A class of tests for equality of ordered means. Biometrika 76:161-168.
• McDermott, M. P. and Mudholkar, G. S. (1993). A simple approach to testing homogeneity of order constrained means. Journal of the American Statistical Association 88:1371-1379.
• Mudholkar, G. S., McDermott, M. P., and Aumont, J (1993). Testing homogeneity of ordered variances. Metrika 40:271-281.
• Mudholkar, G. S., McDermott, M. P., and Mudholkar, A. (1995). Robust finite-intersection tests for homogeneity of ordered variances. Journal of Statistical Planning and Inference 43:185-195.
• Wang, Y. and McDermott, M. P. (1998). Conditional likelihood ratio test for a nonnegative normal mean vector. Journal of the American Statistical Association 93:380-386.
• Wang, Y. and McDermott, M. P. (1998). A conditional test for a nonnegative mean vector based on a Hotelling's T²-type statistic. Journal of Multivariate Analysis 66:64-70.
• Zou, K. H. and McDermott, M. P. (1999). Higher-moment approaches to approximate interval estimation for a certain intraclass correlation coefficient. Statistics in Medicine 18:2051-2061.
• McDermott, M. P. (1999). Generalized orthogonal contrast tests for homogeneity of ordered means. Canadian Journal of Statistics 27:457-470.
• McDermott, M. P. and Wang, Y. (1999). Comment on "The Emperor's new tests" by M. D. Perlman and L. Wu. Statistical Science 14:374-377.
• Wang, Y. and McDermott, M. P. (2001). Uniformly more powerful tests for hypotheses about linear inequalities when the variance is unknown. Proceedings of the American Mathematical Society 129:3091-3100.
• McDermott, M. P. and Wang, Y. (2002). Construction of uniformly more powerful tests for hypotheses about linear inequalities. Journal of Statistical Plannning and Inference 107:207-217.
• McDermott, M. P., Hall, W. J., Oakes, D., and Eberly, S. (2002). Design and analysis of two-period studies of potentially disease-modifying treatments. Controlled Clinical Trials 23:635-649.
• Kost, J. T. and McDermott, M. P. (2002). Combining dependent p-values. Statistics and Probability Letters 60:183-190.
• Natarajan, R., Mudhoklar, G. S., and McDermott, M. P. (2005).  Order-restricted inference for the scale-like inverse Gaussian parameters.  Journal of Statistical Planning and Inference 127:229-236.
• Kost, J. T. and McDermott, M. P. (2008).  Testing equality of means under order restrictions using multiple contrasts. Communications in Statistics, Part A – Theory and Methods (in press).
• He, H., Lyness, J. M., and McDermott, M. P. (2008). Direct estimation of the area under the receiver operating characteristic curve in the presence of verification bias. Statistics in Medicine (in press).