Reading the results

The Results step turns a run into a decision. It opens with the answer, then lets you dig into why, compare configurations fairly, and confirm the winner before you act.

The recommendation

A banner at the top names the configuration that did best on your goal and says, in plain numbers, how much better it is than your current model and how sure that is, for example three entities better at 95 percent confidence. It never claims a single perfect answer it cannot back up.

Ranked results

Below it, every configuration is listed in order, with its factor settings on the left and its responses on the right. Sort by any response, and use Save as Scenario on a row to keep that configuration.

Rows marked Best Group are the ones that are statistically tied for first: within the run’s precision you cannot tell them apart, so the table says so rather than pretending the top row is uniquely best. That is often good news, because it means you can choose among the leaders on cost or simplicity.

What mattered, and how

The main effects chart shows how much each factor changed the result as it moved across its tested range, biggest mover at the top. Compare with baseline puts the leading configurations next to your current model as points with 95 percent confidence ranges, so a difference only reads as real when the ranges are clear of each other. For the full statistics behind the picture, open the detail from the button below the chart.

Where the sweet spot is

For two numeric factors, the sweet-spot map predicts the result across the whole area from the points that ran, with darker meaning better for your goal and a star on the best predicted point. It fills in the gaps between the configurations you actually ran, and tells you how much to trust the prediction.

Confirm the winner

A fast search can be fooled by a lucky run, so Confirm the Winner replays the leading configurations with extra replications and checks the lead holds. Sometimes it settles on one clear winner. Sometimes, as here, the leaders are still tied even after the extra runs, and it tells you plainly: run more replications, or treat them as equally good and choose on cost or simplicity. Either way, you commit on evidence, not on a single run.

Keeping a result

When you have chosen, Save as Scenario copies that configuration into your model as an ordinary scenario, turned off and ready to enable. Export Results saves the full ranked table as a spreadsheet. Everything else clears when you close the experiment.