- Professor of Statistics
- Ph.D., University of Wisconsin-Madison,
1978
- Personal
web site
Summary of research interests
The research efforts of Dr. Akritas are both
methodological and interdisciplinary. The main
methodological thrust involves nonparametric
models for factorial designs with or without
continuous covariates. In the context of the
nonparametric models, new concepts for interaction
effects, main effects, and simple effects, called
nonparametric effects, have been introduced.
Test statistics for these hypotheses use a combination
of rank methods and smoothing techniques. These
allow a unified method for analysis of different
types of data sets (discrete and continuous
ordinal data), as well as different types of
incomplete data (mainly censored and missing)
and dependent data. More recently this fully
nonparametric approach to inference has been
applied to high-dimensional-low-sample-size
cases, including functional data. Current interdisciplinary
work involves the social and medical sciences.
Dr. Akritas is a Fellow of the American Statistical
Association and the Institute of Mathematical
Statistics. He has supervised 13 Ph.D. dissertations
as of 2004.
Representative Publications
M. Akritas and N. Papadatos. 2004. Heteroskedastic
one-way ANOVA and lack-of-fit tests. J.
Amer. Statist. Assoc. 99: 368-382.
H. Wang and M. G. Akritas. 2004. Rank tests
for ANOVA with large number of factor levels.
J. Nonparam. Statist. 16: 563-590.
Y. Du, M. G. Akritas and I. Van Keilegom. 2003.
Nonparametric analysis of covariance for censored
data. Biometrika 90: 269-287.
M.G. Akritas, J. Kouha and W. Osgood. 2002.
A nonparametric approach to matched pairs with
missing data (with discussion). Sociological
Methods & Research 30: 425-462.
J. O’Gorman and M. G. Akritas. 2001.
Nonparametric models and methods for designs
with dependent censored data. Biometrics
57: 88-95.
M. G. Akritas. 2000. The central limit theorem
with censored data. Bernoulli 6: 1109-1120.
M. G. Akritas, S. F. Arnold and Y. Du. 2000.
Models and methods for nonlinear analysis of
covariance. Biometrika 87: 507-526.
I. Van Keilegom and M. G. Akritas. 1999. Transfer
of tail information in censored regression models.
Annals of Statistics 27: 1745-1784.
Last updated:
24 February 2005
|
