Choose a dataset
Five real U.S. datasets. Each one leads to a different outcome.
Upload your data
A CSV file with one column per variable. Put the dependent variable first; a date column is optional.
Drop a CSV file here, or
Your file is analysed on your own device and is not uploaded anywhere. Transform your variables first (logs, growth rates) as your paper requires. Up to 8 variables, at least 30 rows. Format examples: returns.csv, rates.csv.
Answer from your own results
Use this if you have already run unit-root and cointegration tests. If you have not, choose “Use my own data” and the tests are run and explained for you.
Model guides
Routes to a finished paper
Each guide takes one real dataset through estimation, diagnostic tests and writing, with Python code, real output and sample text for the paper.
How the tool decides. A series is treated as stationary, I(0), if the ADF test rejects a unit root in levels at 5%; as I(1) if it rejects only after first differencing. The KPSS test is reported as a cross-check, and the tool warns you when the two disagree. When every series is I(1), the Johansen trace test decides between VAR and VECM. These are standard rules, but tests have low power in short samples and can be distorted by structural breaks, so treat the result as a starting point and justify the choice in your paper.