Learn with runnable examples

Open and import data

• Open a .dta file onlineLoad a bundled Stata-format dataset and inspect its variables.
• Import a CSV with import delimitedLoad a delimited file and verify its rows, types, and missing values.
• Run a do-file in the browserKeep commands in a reusable script and run them without a desktop installation.
• Run a browser workflow on a ChromebookPrepare a zero-install classroom workflow on a managed device.

Create and clean variables

• Calculate row means and totals with egenUse rowmean(), rowtotal(), mean(), count(), and group() in one runnable example.
• Report, tag, and drop duplicate recordsChoose a key, inspect repeated rows, and verify duplicate removal.
• Generate variables and cumulative sumsCreate calculated variables, indicators, and ordered running totals.
• Replace selected and missing valuesChange a checked subset while preserving the rest of a variable.
• Recode values and rangesMap numeric ranges into labeled categories without changing the source.
• Reshape data from wide to longConvert repeated measurements between column and row layouts.
• Merge datasets by an identifierJoin files and diagnose matched and unmatched observations.

Summarize and compare groups

• Summarize variables by groupCalculate counts, means, standard deviations, ranges, and grouped summaries.
• Select statistics with tabstatBuild compact summary tables for several variables and groups.
• Create a frequency table with tabulateBuild one-way and two-way tables of categorical variables.
• Collapse data by groupReplace observation-level rows with grouped means and counts.
• Run a two-sample t-testCompare two group means with a confidence interval and p-value.
• Run a Wilcoxon rank-sum testCompare two independent groups with ranks, exact inference, and porder.

Correlation and regression

• Calculate a correlation with correlate or corrBuild a Pearson correlation matrix and inspect its analysis sample.
• Calculate pairwise correlations with pwcorrUse the observations available for each pair of variables.
• Run an OLS regressionFit a model with categorical predictors and robust standard errors.
• Run a logit regressionFit a binary-response model with robust standard errors.

Predictions and diagnostics

• Predict regression residuals and fitted valuesCreate residuals, fitted values, and standard errors after regression.
• Review runnable supported commandsCheck the implemented command language before adapting a larger workflow.

Replicate published research

• Explore one-click paper replicationsRead about published economics papers and their browser replication workspaces.

Check compatibility before adapting an example

Each example documents the stats.camp behavior it actually uses. An existing do-file can still depend on other options, stored results, user-written packages, or exact formatting that is not implemented.

Review the maintained command and limitation table before moving a consequential workflow.