When I perform a directional t-test in JASP (A > is the null then no difference (A = or its complement (A <= ? I know that in correlations in JASP it is compared to the 'no difference' hypothesis, so assume it is the same for t-tests, but wanted to make sure before I write it up.

Terribly sorry for the 'B )' that turned into the cool shades emoticon. This should be the text:

When I perform a directional t-test in JASP ( A > B ) is the null then no difference ( A = B ) or its complement ( A <= B )? I know that in correlations in JASP it is compared to the 'no difference' hypothesis, so assume it is the same for t-tests, but wanted to make sure before I write it up.

Hi Kevin. The null is always the absence of an effect (i.e., a point null). In one of the next blog posts on BayesianSpectacles.org, I will explain how you can obtain the test for direction from two directed tests against the point null.
EJ

## Comments

13Terribly sorry for the 'B )' that turned into the cool shades emoticon. This should be the text:

When I perform a directional t-test in JASP ( A > B ) is the null then no difference ( A = B ) or its complement ( A <= B )? I know that in correlations in JASP it is compared to the 'no difference' hypothesis, so assume it is the same for t-tests, but wanted to make sure before I write it up.

392Hi Kevin. The null is always the absence of an effect (i.e., a point null). In one of the next blog posts on BayesianSpectacles.org, I will explain how you can obtain the test for direction from two directed tests against the point null.

EJ