inferential statistics

Question 1

what is a significant result?

Answer 1

where there is low probability that the difference or correlation between your variables was due to chance

Question 2

what does collecting significant data allow us to do? (2)

Answer 2

● accept the alternative / experimental hypothesis

● and reject the null hypothesis

Question 3

what is the accepted level of significance in psychology? (2)

Answer 3

● 0.05

● p (probability) ≤ 0.05

Question 4

why do we use the 0.05 level? (4)

Answer 4

● it allows room for some error but not too much

● it gives the right balance of certainty and flexibility needed in research

● it is the most commonly used and accepted level of significance in psychology

● it reduces the chance of making a type I or type II error

Question 5

what is a type I error? (3)

Answer 5

● can occur if the significance level is too lenient e.g. p ≤ 0.1 (10%)

● therefore, we accidentally accept the alternative hypothesis, when we should accept the null hypothesis

● the results are not signifiant but we think they are (false positive)

Question 6

what is a type II error? (3)

Answer 6

● can occur if the significance level is too strict e.g. p ≤ 0.01 (1%)

● therefore, we accidentally accept the null hypothesis, when we should accept the alternative hypothesis

● the results are significant but we think they are not (false negative)

Question 7

what should we ask ourselves to choose a statistical test? (3)

Answer 7

● are we looking at a difference or correlation?

● in the case of a difference, what experimental design is used?

● what level of measurement is used?

Question 8

list all the statistical tests in psychology (8)

Answer 8

● chi-squared

● sign test

● chi squared

● mann-whitney u

● wilcoxon

● spearman’s rho

● unrelated t-test

● related t-test

● pearson’s r

Question 9

what mnemonic can we use to remember the statistical test table?

Answer 9

Carrots Should Come Mashed With Suede, Under Roast Potatoes

Question 10

how do you calculate statistical significance? (3)

Answer 10

● the calculated value (from the statistical test) must be compared with a critical value

● this number tells us whether or not we can reject the null hypothesis and accept the alternative hypothesis

● each stat test has its own table of statistical values

Question 11

what are the criteria for finding which critical value to use? (3)

Answer 11

● one tailed (directional) or two tailed (non directional) test

● the number of participants in study

● the level of significance

Question 12

how do you write a significance statement? (4)

Answer 12

● state whether the results are significant or not significant

● give the level of significance and n / df

● compare the calculated and critical values and state these values

● state which hypothesis should be accepted and which rejected

Question 13

what are the 3 criteria needed to use the sign test?

Answer 13

● difference

● nominal data

● repeated measures

Question 14

how do you work out the calculated value of a stats test? (3)

Answer 14

● put +, - or = in sign (difference) column

● count +, - and = (write them down)

● pick lowest out of + or - (this is the S value / calculated value)

Question 15

how do you work out the critical value (from the critical values table? (5)

Answer 15

● work out N (number of participants - number of =’s)

● identify type of hypothesis (one or two tailed) and what significance level (p value)

● use critical value table to find the critical value

● if your S value is equal to or lower than critical value, results are significant

● if S value is greater than the significance value, results are not significant