In this article:

A stat test, or more formally a hypothesis test seeks to find out if an observed effect is real or if it is random. To do this we compare an observation from a sample to some other expectation. For example, we may observe in a study that women like chocolate more than men, and we could stat test this against the expectation that men and women like chocolate equally.

You can learn more about Dig One's Stat testing methodology here.

Using stat testing in Idea Splits is simple — just toggle the ‘Stat Testing’ button.

For the Stat Testing to work, you will need to pin the idea you want to test all other ideas against by selecting the pin button.

If a result is highlighted, it is statistically significant.

• Green — higher than the pinned idea in a statistically significant way.

• Red — lower than the pinned idea in a statistically significant way.
​

1. Turn On Stat Testing

Within your completed study, in the Idea Screen reporting, toggle Stat Testing on and choose a confidence level.

2. Select a Benchmark Idea

By default, the first idea is selected.
Other ideas will show:

Ideas will only show the arrow if there is a statistical difference to your benchmark. Click any idea to view detailed stats or set a new benchmark.

3. Filter & Sort

4. View Results in Bar Chart

Stat testing is automatically applied to the Bar Chart view.

5. Hover for Tooltips

Hover over ideas or charts for quick tips on stat testing, confidence levels, and color meanings.

6. Export Your Results

Export as Excel, PowerPoint, or Image using the export function in the top right corner of your Idea Screen.

Customize your report to include stat testing results and export it as Excel, PowerPoint, or an Image (PNG/SVG).

Confidence level is how confident we are that the answers are representative. Testing at a 95% level means we'll only find significance when there is less than 5% chance the difference is random. In other words we are 95% confident the difference in results is non-random.