Please enable JavaScript.
Coggle requires JavaScript to display documents.
PROBABILITY AND SIGNIFICANT - Coggle Diagram
PROBABILITY AND SIGNIFICANT
Numerical measure of the likelihood or chance that certain events will occur
Accepted level of probability is 0.05
This means that the likelihood that the results occurred due to chance/luck is equal to or less than 5%
We can never be 100% certain of results as we cant test everyone – but 95% certain is pretty good!
What does p<0.05 mean?
Probability that the difference was caused by chance is less than 5%
It the p value in a test meets this p<0.05 then you can reject the null hypothesis
Probability
p=0.01 (1% likelihood the results are due to chance)
p=0.10 (10% likelihood the results are due to chance)
There are different p values that can be used
What is p<0.01?
Very strict test
It the p value in a test meets this p<0.01 then you can reject the null hypothesis
Probability that the difference was caused by chance is less than 1%
Significance
Level of probability (p) at which it has been agreed to reject the null hypothesis
Type 1 error:
Rejecting a null hypothesis that is true
Likely if the significance level is too high (10%)
Claim to find a significant difference when one does not exist
Type 2 error:
Accepting a null hypothesis that is in fact false
More likely to happen when the significance level is too low (1%)
This is a very strict test so many results do not show a significant difference (even when a significant difference does exist)
Claim to find no significant difference when one does actually exist
An example:
Null hypothesis: alcohol will not have an effect on the number of words a person can recall in 30 seconds
Type 1 error (p=0.10): reject the null and claim that alcohol does influence memory
This is an easy test to pass so most times will show a significant difference
Type 2 error (p=0.01): accept the null and claim that alcohol does not influence memory
This is an strict test to pass so most times will not show a significant difference
What is the chance of a type 1 or type 2 error occurring?
Depends on the p value used
P=0.05
Chance of a type 1 or 2 error occurring is 5%
If the level of significance is set at 5%, there will always be a one in twenty chance or less that the results are due to chance rather than to the influence of the independent variable or some other factors
P=0.01
Chance of a type 1 or 2 error occurring is 1%
How to prevent type 1 and type 2 errors?
Use p=0.05