Hypothesis Testing

Question 1

What is a hypothesis test?

Answer 1

A hypothesis is a statement (an idea) made about the value of a population parameter. You can test a hypothesis through an experiment or from taking a sample of the population.

Question 2

What is a test statistic?

Answer 2

The result of the experiment or the statistic calculated from the sample.

Question 3

What is a null hypothesis?

Answer 3

H0
This is the default position, i.e. nothing is biased, nothing changes or
nothing works - you assume to be correct.

Question 4

What is an alternative hypothesis?

Answer 4

H1
This states that there has been a change - your assumption is shown
to be wrong.

Question 5

What is a one-tailed test?

Answer 5

This states that there will be a change in a specified direction.
i.e H1:p>0.5 or H1:p<0.5

Question 6

What is a two-tailed test?

Answer 6

This states that there has been a change but doesn’t specify direction.
i.e H1: p ≠ 0.5

Question 7

What is the significance level?

Answer 7

We consider how likely the observed value of the test statistic was to occur
If it is less than a given threshold, called a significance level, then you can reject the null hypothesis.
If it is not, then there isn’t sufficient evidence to reject the null hypothesis.
Typically 1, 5 or 10%

Question 8

What is the critical region?

Answer 8

The critical region is the set of values which lead to rejecting the null hypothesis.

Question 9

What is the critical value?

Answer 9

The critical value is the first value to fall inside the critical region.