Graduate Certificate

Educational Data Science

College of Education, Health, & Human Sciences

Program Overview

The University of Tennessee, Knoxville, offers an online graduate certificate in Educational Data Science for students interested in digital data collection, analysis, visualization, and more in educational settings. The certificate can be added to current graduate students’ studies or pursued as a stand-alone certificate for graduate-level students.

Credit Hours

12

Cost Per Credit Hour*

In-State $700

Out-of-State $775

Modality

Synchronous

Admission Terms

Fall, Spring

*Cost per credit hour is an estimate based on maintenance and university fees. Some programs may have additional course fees. Please contact your department for additional information on any related fees, and visit Tuition and Fees in Detail at One Stop.

ACQUIRE THE SKILLS TO BE A LEADER IN EDUCATIONAL DATA SCIENCE

The Educational Data Science Graduate Certificate is designed for graduate students interested in new-often digital-data sources and analytic methods in educational contexts. While there are courses and workshops designed to enable researchers to work with digital sources of data and accompanying methods, they are not widespread. At the same time, there is growing student interest in and demand for courses that equip them to work with more complex and varied sources of data, including data from course learning management systems and social media-based professional networks for educators.

The certificate objectives include:

  • Wrangling data and the tidy data format
  • Introduction to data visualization
  • Ethics, privacy, and justice in the context of data science
  • Posing questions that can be answered using digital data sources, including data from learning management systems
  • Accessing and working with structured (from databases/APIs) and unstructured (e.g., text) data
  • Introduction to functional programming for preparing complex datasets
  • Creating static and dynamic data visualizations using R
  • Using modeling interfaces (e.g., tidymodels) for specifying a range of inferential and machine learning models
  • Exploring useful and ethical applications of machine learning in education
  • Estimation and inference in the context of larger datasets

Featured Courses

In addition to a capstone project, the following courses are required:

STEM 580: An Introduction to Data Science Methods in Education

Intended to support graduate-level students to be able to apply data science methods to topics of teaching, learning, and educational systems. Introduces students to the data science software and programming language R. Course activities focus on preparing and using complex data sources for analysis using the tidyverse suite of R packages. No pre-requisites or programming experience is required.

STEM 585: Digital Learning Environments & Learning Analytics

Intended to support students to study new teaching and learning environments, such as online courses, educational technology platforms, and social media-based networks. Intended to support students to gain experience a) posing questions that can be answered using digital data sources, b) accessing and working with structured (from databases/APIs) and unstructured (e.g., text) data, and c) gaining an introduction to functional programming for preparing complex datasets. The course involves the use of the statistical software R.

STEM 591: Visualize Data Using R

Intended to support students to create static visualizations (e.g., visualizations for inclusion in presentations and publications) and dynamic visualizations (e.g., those that can allow researchers and others to interact with the visualization). Will use educational examples and data sets but is open to students across programs. The course involves the use of the statistical software R.

STEM 595: Predictive Modeling & Machine Learning in Education

Intended to support students to use predictive analytics and machine learning in educational contexts. Intended to support learners in the following: a) using modeling interfaces (e.g., tidymodels) for specifying a range of inferential and machine learning models, b) exploring useful and ethical applications of machine learning in education, and c) estimation and inference in the context of a larger dataset. The course involves the use of the statistical software R.

Ready to advance your career in educational data science? 

Loading...