Datalad tool

The Peeking Simulator

Run a few hundred A/B tests where the variant does absolutely nothing, and watch how many you would have called a winner. Look once at the end and it is about one in twenty, exactly as promised. Check every day and stop when it goes green, and it is far more.

1

Set up the experiment

These are the settings of a single A/B test. The simulator then runs that same test many times over, with fresh random data each time.

Per cent
Split evenly
The planned length
Change it to reshuffle
View Comments (3)

Leave a Reply

Subscribe to My Newsletter

Subscribe to my email newsletter to get the latest posts delivered right to your email. Pure inspiration, zero spam.