The formal process of null hypothesis testing relies on a specific sequence of logical steps to decide between interpretations of a statistical relationship. First, researchers temporarily assume that the null hypothesis is true (i.e., there is no relationship in the population). Second, they determine the probability of obtaining their sample relationship under this assumption. Finally, if the sample result is extremely unlikely given a true null hypothesis, they reject the null hypothesis in favor of the alternative hypothesis; if the result is not extremely unlikely, they retain the null hypothesis.