This intensive is a 3-day presentation of the D-Lab’s introductory Stata workshop series. The intensive will cover the following materials:
Part I: Introduction (Monday, August 15)
- Getting a dataset into Stata (no previous knowledge expected)
- Examining a dataset and finding variables of interest
- Summarizing and tabulating variables
- Stata specific tools and resources (do files, logs, help files, etc.)
- Coding and cleaning data (making new variables from old variables; labeling variables and values, etc.)
- Using logical operators in Stata
- Cross-tabulations
Part II: Data Analysis in Stata (Tuesday, August 16)
- Correlation
- T-tests
- OLS and logistic regression (basic syntax, using interaction terms, interpreting output)
- Visualization (histograms, bar graphs, scatter plots)
- Regression postestimation (getting predicted values, basic graphs)
- Merging and appending datasets
Part III: Stata Programming (Wednesday, August 17)
- Local and global variables (macros)
- Looping (foreach, forvalues)
- Reshaping data between wide and long formats
- Recalling and using command output
- Generating nicely formatted journal-style tables
Prerequisites
A basic understanding of variables (nominal, ordinal, continuous), descriptive stats (mean, standard deviation), correlation, and regression would be assumed.
You do not need to bring your own computer as this workshop will be held in a computer lab with access to Stata. If you bring your computer, you can install a trial version of Stata, but please arrive 15 minutes early.
