MC Donohue
  • -
Categories
All (6)
AAIC2016 (1)
composites (1)
constrained longitudinal data analysis (1)
covariates (1)
cross-validation (1)
disease time (1)
gls (1)
GLS (1)
grace (1)
lme (3)
mixed-effects (3)
MMRM (2)
nlme (3)
power (3)
pre-post (1)
preclincal AD (1)
R (3)
simulation (3)

Michael C Donohue, PhD

Professor, Department of Neurology

Associate Director of Biostatistics
USC Epstein Family Alzheimer’s Therapeutic Research Institute
Co-Lead, Biostatistics Unit
Alzheimer’s Clinical Trial Consortium
Keck School of Medicine of USC
University of Southern California
9860 Mesa Rim Rd
San Diego, CA 92121
mdonohue@usc.edu

About

Michael Donohue is Professor of Neurology at the Keck School of Medicine and Associate Director of Biostatistics at the Epstein Family Alzheimer’s Therapeutic Research Institute (ATRI). He received his PhD in Mathematics from the University of California, San Diego. Dr. Donohue applies novel statistical methods to data from natural history studies and clinical trials to better understand the multivariate course of markers of Alzheimer’s progression, and design innovative clinical trials to prevent or slow the progression of disease. He has studied the risk of cognitive decline associated with elevated brain amyloid in cognitively normal individuals; and helped design the first intervention in asymptomatic Alzheimer’s, the Anti-Amyloid Treatment for Asymptomatic Alzheimer’s (the A4 Study; in collaboration with Eli Lilly), and its primary outcome measure, the Preclinical Alzheimer Cognitive Composite. He has been awarded grants to develop innovative statistical approaches for Alzheimer’s from the National Institute on Aging; the Alzheimer’s Association, Michael J. Fox Foundation, and W. Garfield Weston Foundation; and the Clinical and Translation Research Institute of the University of California, San Diego

Principal Research Interests

  • Modelling long-term evolution of neurodegenerative diseases
  • Semiparametric and generalized linear mixed-effects models
  • Model selection
  • Clinical trials design
  • Missing data
  • Alzheimer’s Disease clinical trials

Collaborative Projects

  • Alzheimer’s Therapeutic Research Institute (ATRI)
  • Alzheimer’s Clinical Trial Consortium (ACTC)
  • Alzheimer’s Disease Neuroimaging Initiative (ADNI)

Publications

See pubmed for full list of publications

Posts

Constrained vs unconstrained longitudinal data analysis

mixed-effects
lme
nlme
R
constrained longitudinal data analysis
power
simulation
pre-post
Liang and Zeger (2000) describe a constrained longitudinal data analysis for comparing the time course of two randomized groups in which the model constains the two groups…
Oct 21, 2016
 

Cross-Validation of Optimized Composites for Preclinical Alzheimer’s

AAIC2016
composites
cross-validation
preclincal AD
Slides from PIA Day at AAIC 2016: Clinical Trials Advancement and Methods
Jul 25, 2016

GLS, MMRM, and Power

mixed-effects
MMRM
gls
lme
nlme
R
power
simulation
We use the power calculation formula of Lu, Luo and Chen (2008) for Mixed Models of Repeated Measures, which accomodates general missing data patterns. This formula is…
Apr 15, 2014

Covariates and Power

covariates
power
simulation
We run some simple simulations to demonstrate the effect of covariates on power.
May 14, 2013
 

GLS, MMRM, and Missing Data

GLS
MMRM
mixed-effects
lme
nlme
R
The gls routine in the nlme package is sensitive to the data order when using corCompSymm, particularly when data is missing. This is alluded to in the corCompSymm documentat…
May 6, 2013

grace: Growth curves by Alternating Conditional Expectation

disease time
grace
Diseases that progress over long periods of time are often studied by observing cohorts at different stages of disease for shorter periods of time. We apply an Alternating…
Jul 18, 2012
No matching items