9- probability and statistical significance

Question 1

define level of statistical significance

Answer 1

• level at which the decision is made to reject the null hypothesis in favour of the experimental hypothesis
• how sure we can be that IV has and effect on DV

Question 2

define chance

Answer 2

something has no real cause, it just happens

Question 3

define probability

Answer 3

numerical measure that determines if results are due to chance or if there is a real difference

Question 4

what is the standard level of significance and why is it used

Answer 4

• p<0.05 (5% level)
• not too strict or too lenient (middle, fair value)
• minimises chances of a Type 1 or Type 2 error

Question 5

when are 5% significance levels usually used

Answer 5

when there is a directional one tailed hypothesis

Question 6

what does a 10% level of significance suggest

Answer 6

there is a 10% margin of error and we can be 90% certain that results are showing a significant difference

Question 7

why is a 1% significance levels sometimes used

Answer 7

• research findings are critical
• e.g. testing effects of drugs on human
• must ensure results are not due to chance

Question 8

what is a type I error

Answer 8

• reject null hypothesis
• but results are due to chance and not statistically significant
• mistake was made and null hypothesis should have been accepted

Question 9

what is a type II error

Answer 9

• accept null hypothesis
• but results are due to chance and not statistically significant
• mistake was made and null hypothesis should have been rejected