What does it mean to reject the null hypothesis


Null hypothesis


Next page:Alternative hypothesis Upwards:Test procedure Previous page:Hypothesis test & nbsp index

As Null hypothesis (English: null hypothesis) is the term used to describe the assumption about the “population” to be tested in the context of a “hypothesis test”. The assumption that is actually of interest, the so-called assumption, is often not chosen as the null hypothesis Working hypothesisbut the assumption that you want to refute. This indirect evidence confuses most users, but is due to the fact that many interesting assumptions about parameters of the population can only be formulated very unspecifically.

In order to be able to carry out a hypothesis test, however, one needs an exact assumption in order - based on this assumption - to simulate conceivable sample results and to compare them with the data of the sample collected. If such an exact specification, as in many cases, is only possible for the opposite of the actually interesting working hypothesis, then it is the starting point of the test procedure.

A positive test result initially means nothing more than that the null hypothesis has been refuted. This implicitly confirms the assumption that is actually of interest (in the example the assumption of greater income losses for women), with what certainty this "alternative hypothesis" was confirmed, is not the subject of the test procedure. In order to be able to calculate the probability with which the alternative hypothesis was confirmed, the presumed difference in income losses would have to be specified (see "Test Strength").

notation: .



Next page:Alternative hypothesis Upwards:Test procedure Previous page:Hypothesis test & nbsp index HJA 2001-10-01