Skip to Main Content
It looks like you're using Internet Explorer 11 or older. This website works best with modern browsers such as the latest versions of Chrome, Firefox, Safari, and Edge. If you continue with this browser, you may see unexpected results.
| University Libraries
See Updates and FAQs for the latest library services updates. Subject Librarians are available for online appointments, and Virtual Reference has extended hours.

Data Analysis & Statistics

Resources on the topics covered in introductory statistics and data analysis classes (e.g., PUBP 511, COMM 650)

Mixed & Multi-level Modeling

  • An Introduction to Hierarchical Modeling
    • Graphical introduction to the concepts, including Random  Intercept and Random Slope
  • LEMMA: Learning Environment for Multilevel Methods and Applications
    • Free (requires registration) course from the center for Multilevel modeling that covers multiple regression and more.
  • Germán Rodríguez
    • Course materials on GLM and GLMM using Stata and R
  • Linear Models and Mixed Models with R by Bodo Winter
    • See Part I and Part 2
    • Although using R, this set of tutorials explains the important concepts

Path Analysis & Structural Equation Modeling (SEM)

Factor Analysis

Time Series & Panel Data Analysis

Issues for Data Over Time

  • Correlation with Time: Two variables are strongly correlated, but it is simply that both trend over time.
    • You can control for the time variable (e.g., year)
    • You can examine the changes from year to year ("Differencing")
  • Monetary Inflation: The value of money is not constant over time, and inflation is not constant either.
  • Time-lagged relationships: One variable may affect the other only after a period of tiem.

Machine Learning

What is machine learning?

Machine learning is a branch of artificial intelligence focusing on the training of statistical models and algorithms that can automatically improve their performance by discovering and retaining patterns these models observe in data (i.e., "learning"). In practice, this means being very accurate at prediction.

This focus on prediction differentiates machine learning from traditional statistical inference in important ways. Machine learning also uses different words than traditional statistics to describe the same thing (e.g., "features" instead of "variables")