Michael C. Donohue, PhD
9500 Gilman Dr, MC 0949
La Jolla, CA 92093-0949
Dr. Donohue's methodological interests include semiparametric and generalized linear mixed-effects models, model selection, asymptotics, and clinical trials design. His applied work includes the design, monitoring, and analysis of clinical trials and observational studies in the fields of Alzheimer's disease, anxiety disorders, fMRI pain response, smoking cessation, and childhood obesity.
Dr. Donohue received his PhD in Mathematics from UCSD in 2005. His thesis work involved related problems in rank regression and synergy detection. He proposed a procedure for fitting a regression surface with linear level sets, which is useful for determining synergy between two or more agents. More recently he been investigating model selection and asymptotics for generalized linear and proportional hazards mixed-effects models. He received a KL2 Post-Doctoral Scholar Award to investigate efficient analysis methods for longitudinal clinical trials, particularly in the face of missing data typical in Alzheimer's disease trials.
Dr. Donohue is a senior statistician on two ongoing Alzheimer's Disease Cooperative Study (ADCS) observational studies: Alzheimer's Disease Neuroimaging Initiative (ADNI) and Home Based Assessments (HBA). Both studies are designed to improve the statistical and economical efficiency of future Alzheimer's disease clinical trials. He has been working on power and study design for prodromal or asymptomatic Alzheimer's disease incorporating recent advances from ADNI in neuroimaging and fluid assay biomarkers. As a statistician with the Clinical and Translational Research Institute (CTRI), he also collaborate with a wide range of researchers across the School of Medicine.
Principal Research Interests
- Semiparametric and generalized linear mixed-effects models
- Model selection
- Clinical trials design
- Missing data
- Alzheimer's Disease clinical trials
- Alzheimer's Disease Cooperative Study (ADCS)
- Alzheimer's Disease Neuroimaging Initiative (ADNI)
- Clinical and Translational Research Institute (CTRI)
- Clinical Research Enhancement through Supplemental Training (CREST)
- Epidemiology, Biostatistics, & Medical Informatics (EBMI), School of Medicine
Selected University & Public Service
- CTSA BERD Reproducible Research Committee
- Donohue MC, Aisen PS. Mixed model of repeated measures versus slope models in Alzheimer's disease clinical trials. J Nutr Health Aging. 2012 Apr;16(4):360-4.
- Donohue MC, Haut R, Xu R, Vaida F. Conditional Akaike information under generalized linear and proportional hazards mixed models. Biometrika. 2011;2:1-16.
- Donohue MC, Gamst AC, Thomas RG, Xu R, Beckett L, Petersen RC, Weiner MW, Aisen P and for the Alzheimer's Disease Neuroimaging Initiative, The relative efficiency of time-to-threshold and rate of change in longitudinal data. Contemporary Clinical Trials. 2011;32:685-693.
- Gamst A, Donohue M, Xu R. Asymptotic properties and empirical evaluation of the NPMLE in the proportional hazards mixed-effects model. Statistica Sinica. 2009;19 (3)
- Donohue M, Abramson I, Gamst A. Asynergistic regression based on maximized rank correlation. Communications in Statistics - Simulation and Computation. 2008;37:92-105.
- Berlin I, Covey LS, Donohue MC, Vito A. Duration of Smoking Abstinence and Suicide Related Outcomes, Nicotine & Tobacco Research. 2011.
- Beckett L, Harvey D, Gamst A, Donohue M, Kornak J, Zhang H, Kuo J, and the Alzheimer's Disease Neuroimaging Initiative. The Alzheimer's Disease Neuroimaging Initiative: Annual Change in Biomarkers and Clinical Outcomes. Alzheimer's & Dementia. 2010;6(3):257-64.
- Petersen R, Aisen P, Beckett L, Donohue M, Gamst A, Harvey D, Jack C, Jagust W, Shaw L, Toga A, Trojanowski J, and Weiner M. Alzheimer's Disease Neuroimaging Initiative (ADNI): Clinical Characterization. Neurology. 2010;74(3):201-9.