# When is a one-sided test used versus a two sided test in a Fisher's Exact Test?

Suppose I have a 2 by 2 table and I am trying to conduct a Fisher's Exact Test. I am wondering when the two-sided test is used versus a one-sided test. In programs like R, they have greater, less, and two-sided. In most cases, I would only use either greater or less depending on the direction. However, when is the two-sided version ever used? Thanks.

If you have a very strong assumption before exploring your data that the values of one group will be either lower or equal to the other group (alternative="less") or that the values of one group will be either higher or equal to the other group (alternative="greater") you can use a one-sided test to increase the power of this test: