power

Question 1

what does effect size estimate

Answer 1

the magnitude of an effect

Question 2

d statistics are use dwhen

Answer 2

the response variable is continuous while the predictor is categorical
- ANOVA

Question 3

r statistics are used when

Answer 3

two variables are continious
- correlation or regression

Question 4

odds ratio is used when

Answer 4

the response variable is binary and the predictor variable is binary or continuous
- logiostic regression

Question 5

what test used to do d statistics

Answer 5

cohens d or hedges d

Question 6

what test used to do r statistics

Answer 6

correlation coefficients including Pearsons, sermons, and pointbiserial

Question 7

what tests used to do odds ratio

Answer 7

comparative risk measurements

Question 8

interpretation if you get cohens d of 0.2

Answer 8

small effect size

Question 9

interpretation if you get cohens d of 0.5

Answer 9

medium effect size

Question 10

interpretation if you get cohens d of 0.8

Answer 10

large effect size

Question 11

interpretation of you get r2 value f 0.1

Answer 11

small effect size

Question 12

interpretation of you get r2 value f 0.3

Answer 12

medium effect size

Question 13

interpretation of you get r2 value of 0.5

Answer 13

large effect size

Question 14

interpretation of you get a 2x2 table value of 1.5

Answer 14

small effect size

Question 15

interpretation of you get a 2x2 table value of 3.5

Answer 15

medium effect size

Question 16

interpretation of you get a 2x2 table value of 9

Answer 16

large effect size

Question 17

what is power in statistics

Answer 17

the probably of correctly finding a real pattern

Question 18

type I error

Answer 18

false positive

Question 19

type 2 error

Answer 19

false negative

Question 20

effect size=

Answer 20

difference in means/SD

Question 21

power increases as effect size ______

Answer 21

increases

Question 22

power increases as sample size ____

Answer 22

increases

Question 23

what influences power

Answer 23

• effect size, alpha (type I error), and sample size

Question 24

two types of power analysis

Answer 24

priori
post hoc

Question 25

when is priori power analysis useful

Answer 25

for setting up a large experiment with some pilot data (can calculate the sample size needed)

Question 26

when is post hoc p[ower analysis useful

Answer 26

useful for deciding how powerful your conclusion is (usually when results were not significant)

Question 27

five steps in conducting a power analysis

Answer 27

1. select the type of power analysis desired (prior post hoc) 2. select the expected study design that reflects your hypothesis of interest (t test, anova, etc) 3. select a power analysis tool that supports your design 4. provide 3 of the 4 parameters (alpha, power, expected effect size) 5. solve for the remaining parameter, usually sample size