Null Hypothesis



The concept of Null Hypothesis is a key concept of statistics.

A hypothesis is an idea or tentative theory NOT supported by hard evidence, usually stating that some relationship exists between two variables. This hypothesis is usually referred to as H1.

The Null Hypothesis is the opposite statement, such as "there is NO relationship which exists between the two variables". It is this statement which is usually tested by statistical tools. The Null Hypothesis is usually referred to as H0.

Before you undertake a complex statistical calculation, you should always formulate the Null Hypothesis H0. Your calculations will then show that:
  • The Null Hypothesis can be rejected in favor of H1 with some degree of certainty (default is 95%)
  • The Null Hypothesis must be accepted
  • The calculations are inconclusive and more information is required

Examples:
  • If you test the idea that people with high income also tend to come from privileged background, you will most likely have to reject the Null Hypothesis H0 and accept H1: usually, there tends to be a correlation between the two factors.
  • If you test the idea that people with high income also tend to be taller, you will most likely have to accept the Null Hypothesis H0 and reject H1:usually, there tends to be NO correlation between the two factors.
Comments