Probability + Statistical significance

Question 1

standard significance level

Answer 1

p<0.05

• not too strict or lenient = middle, fair value of significance
• minimises the chance of making a type 1 or type 2 error

5% probability that results are due to chance/ fluke
95% certain that results are due to real difference between the two sets of data

usually when there is a directional one tailed hypothesis

Question 2

10% significance level

Answer 2

10% margin of error
90% certain that results are showing a significant difference

Question 3

1% significance level

Answer 3

often used when research findings are critical + very important
e.g. testing the effect of drugs on humans
= make sure there is a real difference occurring between the experimental + control conditions and not due to fluke

Question 4

type 1 error

Answer 4

Accepting the experimental hypothesis when the null hypothesis is right (it was actually due to chance)

Question 5

type 2 error

Answer 5

Accepting the null hypothesis even though the experimental hypothesis was correct (real difference in data is overlooked)