Basics of Hypothesis Testing

A significance test is a statistical method used to decide between two competing claims (hypothesis). It helps researchers make conclusions about the population parameters (usually mean or proportion) based on sample data.

A statistical hypothesis is a claim or conjecture concerning a parameter of one or more populations. We’re never a 100% sure with a sample.

A hypothesis being tested is the null hypothesis. Rejecting a null hypothesis leads to accepting an alternative hypothesis.

Writing Conclusions

Alternative - Fail to Reject H-not:

There is insufficient evidence to support the claim that the true percentage of blue M&Ms is greater than 7%.

Null - Fail to Reject H-not:

There is insufficient evidence to justify rejecting the claim that the true percentage of blue M&Ms is at most 7%.

Alternative - Reject H-not:

There is sufficient evidence to support the claim that the true percentage of blue M&Ms is greater than 7%

Null - Reject H-not:

There is sufficient evidence to justify rejecting the claim that the percentage of blue M&Ms is at most 7% and conclude the percentage is more than 7%.