Space-Time Interaction Tests

Space-time interaction tests ask whether cases cluster in space and time together — not just one or the other independently. A disease outbreak that spreads from person to person, for example, produces cases that are close in space and close in time; space-time interaction tests are built to detect that joint pattern, which a purely spatial method like Local Cluster Analysis or a purely temporal one would miss.

Vesta reads event times directly from its own time structure, so no separate manual date entry is required.

These tests work from cases alone. If you have a control group — people who could have become cases but didn't — and want to compare cases against where people actually are rather than against uniformity, see Q-Statistics instead.

Available Tests

• Knox test — compares the observed number of case pairs that are close in both space and time against the number expected by chance.
• Jacquez k-NN test — a nearest-neighbor based test for space-time clustering.
• Direction test — tests whether cases show a directional pattern of spread over time.

Process Steps

1. Click on the "Analyze" button from the side bar menu.
2. Select "Space-Time Interaction" from the available methods.
3. Choose Automatic, Guided, or Full control guidance. See Analysis Introduction for more on the Guided Analyze wizard.
4. Select the dataset containing your case data, and select which test (Knox, Jacquez k-NN, or Direction) to run.
5. Select "Run".
6. Results are saved in the Data panel to the right.