*Topics Short Courses are for current UT Austin faculty, staff, and students.


*Seating for each class is limited to 40 students.

Instructors:  Michael Mahometa, Erika Hale, and Sally Ragsdale are statistical consultants for the Department of Statistics and Data Sciences.  Click here to see their full bios.

Basic Applied Statistics

This course will demonstrate how to use basic statistical techniques, including t-tests, ANOVA, correlation, and nonparametric analyses to answer real-world questions. The emphasis will be on applications and not theory although the concepts behind the techniques will be explained. Stata will be used to perform the analyses; the software is loaded on the classroom computers and is therefore not required of participants. By the end of the course, participants should be able to:

  • Identify basic statistical techniques.
  • Understand the questions each technique answers.
  • Select the appropriate technique for a given research question.
  • Run basic statistical analyses.
  • Interpret results.

Prerequisites: Experience with data and spreadsheets is helpful. An understanding of descriptive statistics, e.g. mean, standard deviation, median, and skewness, is not necessary but will facilitate learning in the class.

 

Understanding regression

This course introduces the basics of correlation, simple linear regression, and multiple linear regression. Attendants will learn how to read and interpret linear regression output from common statistical software packages. Attendants will also learn when linear regression analysis is and is not appropriate, as well as pitfalls and data considerations. This course does not require the use of any particular software, but will provide output and visualizations of analyses.  After completing this course, a new user should be able to:
  • Determine the correct type of data to use in regression analysis.
  • How correlation and linear regression are related.
  • How to interpret simple and multiple linear regression.
  • Assess the validity of data for linear regression.
  • Understand and interpret categorical variables in multiple linear regression.
  • How visualizations help in understanding linear regression.
  • Read and interpret regression output in scientific journals.
Prerequisites: Familiarity with basic statistical concepts such descriptive statistic and as t-tests is recommended but not necessary.

 

introduction to mixed models

This course will introduce participants to linear and generalized linear mixed models, which are regression models with both fixed and random effects, and are also known as hierarchical linear models (HLM). This is an applied course, and we'll see examples of how to run mixed models in several common statistics software packages. By the end of the course, participants should have an understanding of the following:
  • What mixed models are and when they can be used.
  • Using mixed models to analyze longitudinal/repeated measures data.
  • Assumptions and how to check them.
  • How to run mixed models in common statistics software packages.
  • What to look for in the output and how to interpret the results.

Prerequisites: Basic familiarity with multiple linear regression and hypothesis testing is highly recommended. No specific software experience is necessary.