Statistical hypothesis testing 1: Introducing hypothesis testing Flashcards
1
Q
Describe hypothesis testing
A
uses data from a sample to test whether a statement about a whole population is believable or not
2
Q
H0 and H1
A
- H0 represents the null hypothesis
- H1 represents the alternative hypothesis
3
Q
Method for conducting a hypothesis test
A
- establish H0 and H1
- decide on the significance level
- use the data to find the test statistic
- calculate the p-value and compare with significance level
- if p-value < significance level reject H0, else don’t reject H0
- state a conclusion with reference to the context of the question
4
Q
If the test statistic is small…
A
find the P(X<= test statistic)
5
Q
If the test statistic is big…
A
find the P(X>= test statistic)
6
Q
One tail test
A
- test either the bottom end or top end of the tail
- P > … or P < …
7
Q
Two tail test
A
- the significance level is halved and tested on both ends of the tail
- P ≠ …
8
Q
Hypothesis testing conclusion
A
- There is / isn’t sufficient to reject H0
- There is / isn’t sufficient evidence to suggest that … (refer back to context)