Dr. Lennox has more than ten years of experience applying statistics, machine learning, and operations research techniques to scientific and engineering problems. Her expertise includes experimental design, analysis of computer experiments, and risk assessment in high consequence environments. Her career has included data science applications in aerospace, chemical engineering, materials science, process engineering, oil and gas, public infrastructure, bioinformatics, software development, and manufacturing. She has worked with many varieties of data ranging from large publicly available datasets to small scale designed experiments and specializes in combining disparate data types and sources to solve complex problems. She has experience in developing new data science teams in both large and small organizations, as well as educating managers and other non-data scientists on essential concepts such as model bias, explainability, and ethical artificial intelligence (AI).
After completing her PhD in statistics, Dr. Lennox joined Lawrence Livermore National Laboratory (LLNL) where she worked on a variety of scientific and engineering problems, with a research emphasis on design and analysis of computer experiments (DACE), Bayesian statistics, and nonparametric statistics. She co-founded and led the LLNL statistical consulting service, which gave her exposure to diverse areas across the lab including medical surveillance, computer vision, and radiation detection. In addition to serving as a consultant on many projects, she led multidisciplinary efforts in risk assessment and radiation detection.
After leaving the laboratory, Dr. Lennox worked as a Principal Data Scientist for GE Aviation and multiple startups targeting AI applications in industry. Dr. Lennox developed models and other analytics tools to support increased efficiency in manufacturing and materials science and led development efforts for software applications to support both aerospace and chemical manufacturing.
Dr. Lennox is passionate about statistics and AI education and has created a series of videos for engineers and lay audiences on these topics.
CREDENTIALS & PROFESSIONAL HONORS
- Ph.D., Statistics, Texas A&M University, 2010
- M.S., Statistics, Texas A&M University, 2007
- B.S., Applied Mathematics, Texas A&M University, 2005
Parzen Graduate Research Fellowship, Texas A&M University, 2009
National Merit Scholar, Texas A&M University, 2003
Lennox KP, Rosenfield P, Blair B, Kaplan A, Armendariz JR, Glenn A, Wurtz R . Assessing and Minimizing Contamination in Time of Flight Based Validation Data. Nuclear Instruments and Methods Section A 2017; 870:30–36.
Lennox KP, Glascoe L. A Bayesian Measurement Error Model for Misaligned Radiographic Data. Technometrics 2013; 55:450–460.
Day R, Joo H, Chavan AG, Lennox KP, Chen A, Dahl DB, Vannucci M, Tsai JW. Understanding the General Packing Rearrangements Required for Successful Template Based Modeling of Protein Structure from a CASP Experiment. Computational Biology and Chemistry 2013; 42:40-48.
Cadag E, Vitalis E, Lennox KP, Zhou CLE, Zemla AT. Computational Analysis of Pathogen-Borne Metallo β-Lactamases Reveals Discriminating Structural Features Between B1 Types. BMC Research Notes 2012;. 5:96.
Lennox KP, Glascoe L. Constrained Classification for Infrastructure Threat Assessment. Proceedings of the 2011 IEEE Conference on Technologies for Homeland Security 2011; 92–97.
Chavan AG, Joo H, Day R, Lennox KP, Sukhavnov P, Dahl DB, Vannucci M, Tsai JW. Near-Native Protein Loop Sampling using Nonparametric Density Estimation Accommodating
Sparcity. PLoS Computational Biology 2011. 7:e1002234.
Day, R, Lennox KP, Dahl DB, Vannucci M, Tsai JW. Characterizing the Regularity of Tetrahedral Packing Motifs in Protein Tertiary Structure. Bioinformatics 2010; 26:3059–3066.
Lennox KP, Dahl DB, Vannucci M, Day R, Tsai JW. A Dirichlet Process Mixture of Hidden Markov Models for Protein Structure Prediction. Annals of Applied Statistics 2010; 4:916–962.
Lennox KP, Sherman M. Efficient Experimental Design for Binary Matched Pairs Data. Statistics in Medicine 2009; 28:2952–2966.
Lennox KP, Dahl DB, Vannucci M, Tsai JW. Density Estimation for Protein Conformation Angles Using a Bivariate von Mises Distribution and Bayesian Nonparametrics. Journal of the American Statistical Association 2009; 104:586–596.
Mintz, BJ, Lennox KP, Wilson AK. Truncation of the Correlation Consistent Basis Sets: An Effective Approach to the Reduction of Computational Cost? Journal of Chemical Physics 2004; 121:5629-5634.
Lennox, KP. The Minds of Machines. Arab Artificial Intelligence Summit, Sweimeh, Jordan. 2019.
Lennox, KP. All About that Bayes. Lawrence Livermore National Laboratory, Livermore, CA. 2016.
Lennox, KP. Everything Wrong with Statistics (and How to Fix It). Lawrence Livermore National Laboratory, Livermore, CA 2015.
US Patent, 10,078,145: Methods and Systems for Calibration of Particle Detectors, 2018 (Wurtz R, Lennox KP).
Principal Data Scientist, Citrine Informatics, 2019-2020
Technical Head of Industrial IoT, Beyond Limits, 2019
Principal Data Scientist, Beyond Limits, 2018-2019
Principal Data Scientist, GE Aviation, 2016-2018
Director of Statistical Consulting, Lawrence Livermore National Laboratory, 2013-2016
Applied Statistician, Lawrence Livermore National Laboratory, 2010-2016
American Statistical Association (ASA)
Insititute of Mathematical Statistics (IMS)
International Statistical Engineering Association (ISEA)
Editorships and Editorial Review Boards
Statistical Analysis and Data Mining, Associate Editor for Conference on Data Analysis Issue, 2013-2017
Journal of the American Statistical Association
Journal of the Royal Statistical Society Series B
Statistical Applications in Genetics and Structural Biology