Effect Size

Question 1

Effect size

Answer 1

Statistics that estimate the strength or magnitude of the relationship between variables or the difference between two distributions of scores

Question 2

How to minimise many of the consequences of NHST ?

Answer 2

to report and interpret estimates of effect size in addition to the p value.

Question 3

Indices in effect size

Answer 3

r2 for correlations
R2 for regressions

Question 4

When to use cohen’s d?

Answer 4

Differences between means - in Sd

Question 5

Cohen’s (1988) labels:

Answer 5

•r=.10 - small
•r=.30 - medium
•r=.50 – large

Question 6

Cohens labels context

Answer 6

meaning of a finding depends on contextual considerations (.50 might be large in one literature and small in another).

Question 7

practical implications of effects ‘small’ size –

Answer 7

they may be labelled “small” but have large clinical implications.

Question 8

Sometimes small effects are important when ..

Answer 8

• predicting infrequent events
  •When there is little variance in the predictor or outcome.
  •When the outcome is important but resistance to change.

Question 9

correlation co-efficient is a numerical value of the strength and direction of the relationship between the two ariables is also referred to as?

Answer 9

Effect size

Question 10

How is effect size shown for Pearson

Answer 10

lower-case, italised r for Pearsons

Question 11

How is effect size shown for spearman’s

Answer 11

lower-case, italised r with a subscript s for Spearmans