I provide consulting related to:
- Data selection and collection
- Data pre-processing and cleaning
- Data visualization in dashboards
- Data analysis
Contact me to discuss consulting opportunities.
Research and Data Scientist (Lumen Learning, LLC, January 2016 – Present)
Created an automated confirmatory factor analysis and item response theory tool that accepts assessment item data as input and outputs how well each item loads onto outcomes and item difficulty. Handles missing data and polytomous response data. Conducted an analytics project on the continuous improvement of OER using learning analytics. Conducted data preprocessing and statistical analysis on personalized learning system data.
Research Consultant (The Greaves Group, October 2016 – December 2016)
Created and synthesized the current literature on the definition, key elements, and impact of personalized learning (white paper and PowerPoint). Distinguished between adaptive learning, individualized learning, differentiated learning, and personalized learning.
Graduate Researcher (Research with Dr. Charles Graham, April 2014 – Present)
Developed expertise with Canvas (Learning Management System); collected data using the Canvas API and preprocessed it with Python. Explored online learner system data to identify patterns, develop predictive models, and categorize students into groups. Developed real-time learning analytics dashboards and tested their effectiveness using randomized control trials, focus groups, and evaluation surveys.
Graduate Researcher (Research with Dr. Ross Larsen, April 2014 – Present)
Simulated categorical and continuous correlated variables using innovative brute force approach. Conducted weighted propensity score analysis allowing betas in logistic regression to vary or averaging betas across all group comparisons. Used supercomputer to conduct simulation studies.
Quantitative Research Intern (Knod Global Learning, August 2014 – April 2015)
Analyzed survey data. Conducted mean difference testing between groups on various outcome variables.
– Python (pandas, scipy, statsmodel, numpy, matplotlib)
– SQL and NoSQL databases
– JSON, XML, CSV
– Linear regression
– Structural equation modeling
– Factor analysis (exploratory, confirmatory)
– Item response theory
– Support vector machines
– Random forest
– Linear/logistic regression
– Clustering (k-means and hierarchical)
– Brainhoney analytics data
– Canvas analytics data
– Experience API (xAPI) formatted data
– Designing and evaluating dashboards