Front | Back |
NULL HYPOTHESIS |
Start off with this. There is no chance, no difference between exposure and outcome eg. tobacco smoke and lung cancer.
|
H0
|
Null Hypothesis |
Alternative Hypothesis. Yes. There is a difference/association in the population |
H1
|
I FAIL TO REJECT THE NULL HYPOTHESIS.
|
The H0 is true. |
Yes, H1 is true. |
I REJECT THE NULL HYPOTHESIS
|
P VALUERESULT OF CHANCE/PROBABILITY
|
Between 0 and 1 |
UNLIKELY TO BE CHANCEEVIDENCE FOR THE ALTERNATIVE HYPOTHESIS H1 REJECT THE NULL / REAL DIFFERENCE
|
Small P's less than or equal to 0.05 or 5% |
More than 0.05 or 5% |
YES IT WAS CHANCE. REJECT THE NULL (ACCEPT IT) AND CONCLUDE THERE IS NO EVIDENCE OF A REAL DIFFERENCE/ASSOCIATION IN THE POPULATION
|
TYPE 1 ERROR
|
False positive -- A false alarm - Rejecting the null hypothesis when it is true |
A Type II error |
FAIL TO REJECT THE NULL HYPOTHESIS WHEN YOU SHOULD HAVE (IT IS FALSE). HAVE A SUFFICIENT SAMPLE SIZE TO DETECT A DIFFERENT ASSOCIATION IF ONE EXISTS
|