One-Tailed Test

A statistical test for significance of the relation between two variables, where a prior assumption about the direction of the relationship is made (e.g., whether the correlation would be positive or negative, and not only that the correlation is not equal to 0.0 (i.e., less than or greater than 0.0). The name “one-tailed test” reflects the fact that the probability (i.e., the area under the curve representing the distribution of the test statistic) is determined from the area under one of the “tails” (i.e., sides) of the distribution of the test statistic (e.g., the normal distribution). If an a priori directional research hypothesis has been formulated (e.g., “female rats are more inquisitive that male rats” as opposed to “male and female rats differ in their level of inquisitiveness”), then the same observed test statistic value will be associated with a 50% lower probability of error (rejecting the null hypothesis when in fact holds true in the population).