Biography

I am a survey statistician who develops estimation techniques that combine complex survey data with big data sources. Whether it’s to estimate official statistics, related to canopy cover or occupational statistics, or to assess the impact of voter ID laws, I enjoy creating methods to learn from data. I also enjoy teaching my students how to learn from data and introducing them to R (an open source statistical software program). As a firm believer that undergraduate research enhances the educational experience, I involve students in my own work and co-chair two national programs: the Undergraduate Statistics Project Competition and the Electronic Undergraduate Statistics Research Conference.

I enjoy helping my students develop their abilities to think statistically, to understand variability, and to draw sound conclusions from data. The statistical software package R/RStudio plays a prominent role in most of my classes with the students learning a reproducible workflow through creating R Markdown reports.

Spring 2019 Courses:

• Math 343: Statistics Practicum
• Math 392: Mathematical Statistics

Fall 2018 Courses:

• Math 141: Introduction to Probability and Statistics
  • Students can access the RStudio Server here.
  • In the course, we use DataCamp.com a browser-based interactive platform for learning data science.

In many of my research projects, I develop new estimators for complex survey data using modern modeling techniques such as penalized splines, elastic net regression, and regression trees. For several years, I have partnered with the Forest Inventory and Analysis Program to estimate forestry quantities by combining complex sample data with remotely sensed data. For 2016 – 2017, I was an ASA/NSF/BLS Research Fellow and explored statistical learning techniques for estimation and imputation at the Bureau of Labor Statistics.

Current Projects:

• Land cover/land use change estimation in Georgia.
  • Work is part of the grant “Advances in model-assisted and small area estimation strategies for forest inventories.” funded by U.S. Department of Agriculture Forest Service, Rocky Mountain Research Station.
• Domain estimation and calibration using regression trees.
  • Collaboration with Daniell Toth (BLS).
• Mentoring undergraduate research in statistics: Reaping the benefits and overcoming the barriers.
  • Collaboration with Vittorio Addona (Macalester College), Joe Nolan (Northern Kentucky University), Dennis Pearl (Pennsylvania State University), and Nathan Tintle (Dordt College).

Publications:

• McConville, K. S. and C. Schumacher*. (Submitted). Lasso Logistic Regression Estimator.
• McConville, K. S., and E., Remy*. (Submitted) Are Volcanic Eruptions Increasing?: An Example of Teaching Data Wrangling and Visualization.
• McConville, K. S. and D. Toth. (Accepted in the Scandinavian Journal of Statistics). Automated Selection of Post-Strata using a Model-Assisted Regression Tree Estimator.
• McConville, K. S., Stokes, L., and M., Gray. (2018). Accumulating Evidence of the Impact of Voter ID Laws: Student Engagement in the Political Process. Statistics and Public Policy, https://doi.org/10.1080/2330443X.2017.1407721.
• McConville, K. S., Breidt, F. J., Lee, T. C. M., and G. Moisen (2017). Model-Assisted Survey Regression Estimation with the Lasso. Journal of Survey Statistics and Methodology 5, 131-158.
• McConville, K. S. and F. J. Breidt (2013). Survey Design Asymptotics of the Model-Assisted Penalised Spline Regression Estimator. Journal of Nonparametric Statistics 25, 745-763.
• Ayala, J., Corbin, P., McConville, K., Colonius, F., Kliemann, W., and J. Peters (2006). Morse Decompostion, Attractors, and Chain Recurrence. Proyecciones Journal of Mathematics 25, 79-109.