The Power of Replication

The Story

Now you want to replicate your experimental results.

Once again, you are looking for a gene that is associated with a disease. As before, you've narrowed your search down to 100 possible genes. Your experimental design also has the same power and false positive rate as before. This time, however, you can replicate your experiments, and thereby accumulate evidence.

Get to Work

To test new hypotheses, you can test them one at a time or in batches. To replicate an experimental test of a hypothesis, mouse over the hypothesis so that it is highlighted, and click the mouse cursor. You can test each hypothesis a maximum of 12 times. Each test has the same power and false positive rate. When you're ready, check your results to see which hypotheses are actually true.

Up Next...

This exercise shows how replication can seriously improve our assessment of the truth of a scientific hypothesis. Up next, we will discuss how scientists can best use replication, including which kinds of results are the most important to replicate and how the base rate interacts with the need to replicate. After that, we'll play another game to see that things are not so simple when the resources needed for scientific research are limited.


Test new hypotheses and replicate them!

Base rate: Power: False positive rate:
Novel hypotheses: Expected to be TRUE:

Hyp#   Research Findings What do you think?