Kathi Irvine, Ph.D.
I am a Research Statistician with the U.S. Geological Survey at the Northern Rocky Mountain Science Center in Bozeman, Montana.
Research Interest
Prior to finding my home in the federal system in 2011, I was an assistant professor at Montana State University (2008-2010). Since receiving my PhD in Statistics from Oregon State University in 2007, I have collaborated with ecologists and biologists charged with monitoring natural resources on federal and state lands. My team provides statistical support for monitoring programs led by the National Park Service, Fish and Wildlife Service, and state agencies. Our work involves development of survey design and analysis strategies for a variety of plants, animals, and other indicators. We currently support monitoring of whitebark pine in the Greater Yellowstone Ecosystem, upland plant communities throughout the Western US, and bats across North America.
My applied statistical research involves developing analytical approaches for ordinal data and bat acoustic surveys that better link the ecological and observation process within a Bayesian framework, applications of causal analysis, investigating spatial sampling designs, and model-assisted methods for status and trend analyses. I mentor statistics students and support graduate research assistants at Montana State University (MSU). Several of my students have participated in writing peer-reviewed papers during their time at MSU. I encourage students interested in ecological statistics to contact me for possible graduate research assistantships, paid summer work, and other opportunities.
Related Projects:
https://www.whitenosesyndrome.org/
Education and Certifications
PhD. Statistics. Oregon State University
MS. Statistics. Oregon State University; MS. Ecology and Environmental Sciences. University of Maine
BS. Biology. University of North Carolina at Chapel Hill
Science and Products
Book review: BILL SHIPLEY. Cause and correlation in biology: A user's guide to path analysis, structural equations and causal inference with R, 2nd ed. United Kingdom: Cambridge University Press.
Improving geographically extensive acoustic survey designs for modeling species occurrence with imperfect detection and misidentification
Statistical design and analysis for plant cover studies with multiple sources of observation errors
Assessment of imperfect detection of blister rust in whitebark pine within the Greater Yellowstone Ecosystem
Extending ordinal regression with a latent zero-augmented beta distribution
A goodness-of-fit test for occupancy models with correlated within-season revisits
Finally, the magic of Bayesian model notation revealed
Semi-arid vegetation response to antecedent climate and water balance windows
Whitebark pine mortality related to white pine blister rust, mountain pine beetle outbreak, and water availability
Establishing conservation baselines with dynamic distribution models for bat populations facing imminent decline
Meteorological variables to aid forecasting deep slab avalanches on persistent weak layers
Estimating the phenology of elk brucellosis transmission with hierarchical models of cause-specific and baseline hazards
Non-USGS Publications**
**Disclaimer: The views expressed in Non-USGS publications are those of the author and do not represent the views of the USGS, Department of the Interior, or the U.S. Government.
Science and Products
Book review: BILL SHIPLEY. Cause and correlation in biology: A user's guide to path analysis, structural equations and causal inference with R, 2nd ed. United Kingdom: Cambridge University Press.
Improving geographically extensive acoustic survey designs for modeling species occurrence with imperfect detection and misidentification
Statistical design and analysis for plant cover studies with multiple sources of observation errors
Assessment of imperfect detection of blister rust in whitebark pine within the Greater Yellowstone Ecosystem
Extending ordinal regression with a latent zero-augmented beta distribution
A goodness-of-fit test for occupancy models with correlated within-season revisits
Finally, the magic of Bayesian model notation revealed
Semi-arid vegetation response to antecedent climate and water balance windows
Whitebark pine mortality related to white pine blister rust, mountain pine beetle outbreak, and water availability
Establishing conservation baselines with dynamic distribution models for bat populations facing imminent decline
Meteorological variables to aid forecasting deep slab avalanches on persistent weak layers
Estimating the phenology of elk brucellosis transmission with hierarchical models of cause-specific and baseline hazards
Non-USGS Publications**
**Disclaimer: The views expressed in Non-USGS publications are those of the author and do not represent the views of the USGS, Department of the Interior, or the U.S. Government.