Importance of Effect Size

Question 1

what is effect size

Answer 1

objective and standardised measure of the magnitude of an effect

Question 2

what is statistical significance? value?

Answer 2

P<.05

	○ Estimates likelihood the relationship/difference/effect found is down to chance
	○ Doesn't tell anything about size of relationship between variables

Question 3

What does Benjamin et al., (2018) suggest about statistical significance?

Answer 3

○ Stricter alpha level of p<.005 as p<.05 results in a high rate of type 1 errors
○ (α): rejecting H0 when it was true (false positive)
○ Still arbitrary or should it be influenced by the goals of the researchers?

Question 4

effect size and standard normal distribution

Answer 4

• Equivalent to z score of a standard normal distribution
  ○ Standardised: mean = 0, SD = 1
  ○ Describes a values relationship to the mean in terms of SDs from the mean
  • Mean of experimental group is located 0.2 SD above the control group

Question 5

Cohens d effect sizes

Answer 5

small = 0.2
med = 0.5
large = 0.8

Question 6

Pearson’s correlational coefficient: r

range

Answer 6

-1.0 to +1.0

Question 7

cohens guidelines for r

Answer 7

small = 0.1
med = 0.3
large = 0.5

Question 8

R2 – Magnitude of shared variance:

Answer 8

R2 is the amount of variance in variable B that can be attributed to variable A.

Question 9

effect size guidelines for eta squared

Answer 9

small = 0.01
med = 0.059
large = 0.138

Question 10

difference between eat squared and partial eta squared

Answer 10

partial eta squared is often much larger

they calculate the same for one-way anova

Question 11

effect size guidelines for partial eat squared

Answer 11

small = 0.02
med = 0.13
large = 0.26

Question 12

what are odds ratios?

Answer 12

Ratio of the odds of an event occurring in one group compared to another

Question 13

odds ratio

OR < 1

Answer 13

Exposure associated with lower odds of outcome
○ As the predictor variable increases, the odds of the outcome decrease

Question 14

odds ratio

OR > 1

Answer 14

Exposure associated with increased odds of outcome
As the predictor variable increases, so do the odds of the outcome

Question 15

benefits of reporting effect sizes

Answer 15

• Resistant to sample size influence
• Encourages interpreting effects on a continuum
• Used to quantitatively compare results of studies completed in different settings

Question 16

benefits of pooling effect sizes

Answer 16

help resolve inconsistencies in findings

Question 17

pooling effect sizes (meta-analysis)

Answer 17

Estimating size of an effect in population by pooling effect sizes from different studies that test the same hypotheses

Question 18

problems with cohens conventions for effect size

Answer 18

• Misleading labels?
  ○ One size fits all
• Doesn’t consider potentially questionable research practices

Baguley (2009) suggests simple or unstandardised effect sizes may be a more suitable alternative

Question 19

what is logistic regression?

Answer 19

• Regression with a categorical outcome variable/DV
  ○ Predictors/IVs can either be continuous or categorical

Question 20

binary logistic regression - variables

Answer 20

2 dichotomous categories in DV (e.g. presence/absence of dementia)

Question 21

multinomial logistic regression - variables

Answer 21

> 2 categories in DV

Question 22

types of logistic regression

Answer 22

binary
multinomial

Question 23

what does logistic regression tell us?

Answer 23

• Prediction of which, of 2 categories, a person is likely to belong to, given their scores on predictors

Question 24

assumptions of binary LR

Answer 24

multicollinearity
linearity
independence

Question 25

multicollinearity assumption of LR

Answer 25

○ Predictors/Ivs should not be too highly correlated with each other
○ Correlations above .7 are a problem
○ Check VIF and tolerance
§ VIF <10
§ Tolerance >0.1
§ These are ok

Question 26

linearity assumption of LR

Answer 26

○ When outcome variable is categorical this is violated
○ Logistic regression assumes a linear relationship between continuous predictors and the logit of the DV
§ Must transform data using logarithmic transformation
§ Logit is the inverse of the standard logistic function

Question 27

independence assumption of LR

Answer 27

○ Each observation must be independent
○ Observations should not come from repeated measures (before/after) or matched data