Statistical tests

Question 1

What is nominal data

Answer 1

• represented in categorical forms
• e.g. male and female
• discrete data- item can only appear in one category

Question 2

What is ordinal data

Answer 2

• ordered in some way e.g. rating scale
• e.g. first, second and third in a race
• lacks precision as ordering is subjective
• unsafe data- the raw scores need converting into rants to use in the test

Question 3

What is interval data

Answer 3

• based on numberical scales with equal units
• uses scales of measurements e.g. stopwatch, thermometer, weighting scales
• most precise

Question 4

What are inferential tests and how can we use them

Answer 4

• try to infer from the sample data what the population might think
• allow psychologists to draw conclusions from their findings
• these conclusions are based on the probability that a particular pattern of results could have arisen by chance or not
• findings NOT due to chance=significant

Question 5

What probability do psychologists use and why

Answer 5

• 95%- means there is a 5% chance of the results occurring if null hypothesis is true
• probability of 5% recorded at p<0.05

Question 6

Equal to or less than?- explain

Answer 6

• the probability should be EQUAL TO OR LESS THAN 5% (p<0.05)
• meaning there is a 5% chance thta it is not significant

Question 7

If you have SIGNIFICANT results do you which hypothesis do you accept/reject

Answer 7

• reject null

- accept alternative

Question 8

What are critical values

Answer 8

the numerical boundary between acceptance and rejection of the null hypothesis

Question 9

What is the degree of freedom

Answer 9

n-1

Question 10

What is a type 1 error

Answer 10

• false positive
• incorrect rejection of null- need to accept instead
• optimistic error- claiming to have found significant results when they are not
• most likely if significant level is too lenient e.g. 0.05

Question 11

What is a type 2 error

Answer 11

• false negative
• incorrently accepted null- need to reject instead
• pessimistic error- claiming to have found insiginificant results
• most likely if significant level is too stringent e.g. 0.01

Question 12

What do we need to know about our data in order to tell whether we have significance

Answer 12

• level of measurmeent
• type of hypothesis
• experimental design