alternative hypothesis

[noun]

In statistical testing, an alternative hypothesis (H₁) is a statement describing the possibility that an observed result or effect is genuine. The alternative hypothesis is always compared to a null hypothesis (H₀), and H₁ is not accepted until statistical testing shows that it should be accepted in favor of H₀. For example, in an evaluation of data regarding the pain relieving properties of a new drug, the alternative hypothesis would state that the new drug has an effect on pain relief compared to a control. Accepting H₁ does not indicate that the observed result or effect is large or important, simply that it is favored in terms of probability of the outcome.