Skip to main content

Noelle Samia

Associate Professor of Statistics

Ph.D., 2006, University of Iowa

Research Interests

Time-series analysis; Nonlinear time-series modeling with emphasis to threshold models; Statistical inference for infectious diseases and epidemiology; Statistical ecology; Statistical applications to biomedical research.

Research Statement

My research interests focus on introducing and developing new statistical linear and nonlinear (threshold) models. My work is both, theoretical and applied in nature. Through cross-disciplinary collaborations, these advanced and often new statistical methodologies are tailored to each specific application with the aim of explaining the dynamics of complex biological systems, particularly in the areas of infectious diseases and epidemiology, statistical ecology, and biomedical research.

Current Projects

Modeling the spread and persistence of bubonic plague within its host wildlife reservoir. Our research work on bubonic plague has been pivotal in understanding the dynamics of the full eco-epidemiological plague system within its host reservoir and its transmission to humans. Using long-term time-series data on rodents, fleas, and environment across different burrow systems in Kazakhstan, our goal is to investigate the underlying factors involved in explaining the spread and persistence of plague, with the aid of threshold modeling techniques. This work is in collaboration with Professor Nils Chr. Stenseth (CEES, Norway).

Dynamics of methicillin-resistant Staphylococcus aureus (MRSA). We demonstrate, for the first time, that MRSA occupies its own additive epidemiological niche among all-organism nosocomial infections, such that MRSA adds to the total burden of healthcare-associated infections. We are only able to illustrate these findings, by making use of a threshold time-series model. This work is in collaboration with Dr. Lance R. Peterson (NorthShore University HealthSystem).

Predictive threshold models for cholera. Cholera, an acute waterborne diarrheal disease, continues to be a major public health concern in the developing countries worldwide. It has been a central focus of study for several decades. To date, predicting disease propagation and outbreaks has been a challenge to experts. We introduce advanced statistical nonlinear methodologies to successfully predict outbreaks of infectious diseases to humans – thus allowing the implementation of preventive measures before such outbreaks occur. This work is in collaboration with Dr. Rita R. Colwell (University of Maryland).

Factors influencing platelet storage. We study clinically relevant donor-dependent differences in platelet storage properties. Results from the study will enable future studies to identify environmental and heritable storage factors that will improve transfusion therapy. This work is in collaboration with Dr. Thomas J. Raife (University of Wisconsin, Madison).

Bayesian inference of panels of autoregressive time series. We develop new statistical methodologies for panels of linear and nonlinear autoregressive time series of different orders. The model is proven to be useful when applied to the spatio-temporal data of voles in Japan. We show that the statistical models used so far have not been sufficiently sensitive at detecting the detailed and complex density-dependent structure of voles. By applying our new methodologies, we are able to disentangle the role of ecological factors and cyclicity in the local population dynamics. This work is in collaboration with Professor Osnat Stramer (University of Iowa), Professor Nils Chr. Stenseth (CEES, Norway), and Takashi Saitoh (University of Hokkaido, Japan).

Selected Publications

Samia, N.I., Robicsek, A., Heesterbeek, H. and Peterson, L.R. Methicillin-Resistant Staphylococcus Aureus (MRSA) nosocomial infection has its own epidemiological niche and acts as a marker for overall hospital infection control trends. Under revision.

Samia, N.I., Stramer, O., Saitoh, T. and Stenseth, N.C. Climate-driven context-dependent structure of population cycles. Under revision.

Samia, N.I., Kausrud, K.L., Heesterbeek, J.A.P., Ageyev, V.S., Begon, M., Chan, K.S. and Stenseth, N.C. (2011). Dynamics of the plague-wildlife-human system in Central Asia are controlled by two epidemiological thresholds. Proceedings of the National Academy of Sciences, USA, 108 (35), 14527–14532.

Note: Because of its merit, the paper was highlighted by the Editor of Proceedings of the National Academy of Sciences, USA with a special introduction in ‘In this Issue.’

Samia, N.I., Friedman, K.D., Gottschall, J.L. and Raife, T.J. (2011). Hematocrit and C-reactive protein predict treatment response times in ADAMTS13-deficient thrombotic microangiopathy. Journal of Clinical Apheresis, 26 (3), 138–145.

Samia, N.I. (2011). Invited discussion on the paper ‘Threshold Models in Time Series Analysis–30 Years On,’ by Professor Howell Tong. Statistics and Its Interface, 4, 131–132.

Samia, N.I. and Chan, K.S. (2011). Maximum likelihood estimation of a generalized threshold stochastic regression model. Biometrika, 98 (2), 433–448.

Erickson, Y.O., Samia, N.I., Bedell, B., Friedman, K.D., Atkinson, B.S. and Raife T.J. (2009). Elevated procalcitonin and C-reactive protein identify septic inflammation in a subpopulation of thrombotic microangiopathy patients with normal ADAMTS13 activity. Journal of Clinical Apheresis, 24, 150–154.

Samia, N.I., Chan, K.S. and Stenseth, N.C. (2007). A generalized threshold mixed model for analyzing nonnormal nonlinear time series; with application to plague in Kazakhstan. Biometrika, 94 (1), 101–118.

Stenseth, N.C., Samia, N.I., Viljugrein, H., Kausrud, K., Begon, M., Davis, S., Leirs, H., Dubyanskiy, V.M., Esper, J., Ageyev, V.S., Klassovskiy, N.L., Pole, S.B. and Chan, K.S. (2006). Plague dynamics are driven by climate variation. Proceedings of the National Academy of Sciences, USA, 103 (35), 13110–13115.

Back to top