24. Probability & Significance (A2)

Question 1

What is probability?

Answer 1

A measure of the likelihood that a particular event will occur where 0 indicates statistical impossibility and 1 statistical certainty.

Question 2

What is a null hypothesis?

Answer 2

A hypothesis that states nothing will happen or there will be no relationship - H0

Question 3

What is an alternative hypothesis?

Answer 3

A hypothesis that differs from the null as it states there will be a relationship of sorts - it may be directional or non-directional - H1

Question 4

How do we know which hypothesis to accept?

Answer 4

A statistical test tells us whether there is a significant relationship or not and consequently whether we should accept the null or alternative hypothesis

Question 5

What is significance?

Answer 5

A statistical term that tells us how sure we are that a difference or correlation exists. A ‘significant’ result allows the researcher to reject the null hypothesis.

Question 6

What is the typical required level of significance for statistical tests?

Answer 6

0.05 - where there is less than 5% chance the results occurred by chance

Question 7

What is the other required level of significance and when may it be used?

Answer 7

0.01 - this may be used in cases where there is a potential risk to human life - e.g. drug trials

Question 8

What is the critical value?

Answer 8

When testing a hypothesis the numerical boundary of cut-off point between acceptance and rejection of the null hypothesis.

Question 9

How is the critical value important in determining significance?

Answer 9

The calculated value from the stat. test is compared to the required critical value - which differs test to test - for test with an r in the calc. value must be = or > than critical value for others it must be = to or < than the critical value

Question 10

How do you determine which critical value you must compare your calculated value to?

Answer 10

1. Was the study directional or non-directional?
2. How many pcps were there? - the N value
3. What is the required lvl of significance? (0.05/0.01)

Question 11

What is a type 1 error?

Answer 11

The incorrect rejection of a true null hypothesis - a false positive - more likely if the significance level is too lenient say 0.1

Question 12

What is a type 2 error?

Answer 12

The failure to reject a false null hypothesis - a false negative - more likely if the significance level is too stringent say 0.01