In: Statistics and Probability
Since obtaining statistical significance is easier to obtain with the directional hypothesis is one tale tears then anon duration of her part that is to tell tears why would anyone ever design a study with a non directional hypothesis
A non-directional (or two tailed hypothesis) simply states that there will be a difference between the two groups/conditions but does not say which will be greater/smaller, quicker/slower etc. For example:
When the study is correlational, we simply state that variables will be correlated but do not state whether the relationship will be positive or negative, e.g. there will be a significant correlation between variable A and variable B. Thus, when we are simply interested in assessing the significance of difference, instead of going with directional hypothesis, we prefer non-directional hypothesis. I will give a one simpler example, where directional hypothesis can be problematic.
Suppose, we have research hypothesis that present batch of students have shown good performance as compared to previous batch. Suppose, we got research hypothesis rejected and null is accepted. Since it is directional hypothesis, still it is confusing in null hypothesis, whether present batch of students have shown equal performance as compared to previous batch or present batch of students have shown worst performance as compared to previous batch. If we use non-directional hypothesis, this problem be resolved easily, because in case of non-directional hypothesis, our null hypothesis is "present batch of students have shown equal performance as compared to previous batch", thus there will be no confusion as compared to null hypothesis in directional hypothesis.