RES/710 v5
Course Project Worksheet – Calculating
Sample Sizes Using G* Power
Using the G* power website, download the free software and conduct a G* power analysis using the
provided data.
There are 4 types of power analysis (a priori, post-hoc, criterion, and sensitivity). For the purposes of this
class, we will focus on a priori power analysis since it is most commonly used when designing a research
study (Hunt, n.d.).
Using the following parameters, complete a G* power analysis:
Alpha= .05
Power= .80
Expected Effect Size = In Week 2 Discussion 2, we practiced using the “Which Stats Test” Sage Tool.
Refer to the statistical test determined using that tool and select the large effect size for the appropriate
test. (Note: if you aren’t sure which test to use, you can use the t-test family, correlation). You will not
lose points for choosing the incorrect test. The point here is to determine a test, input the
parameters into G*power, and explain the results.
Figure 1 – Effect Size Benchmarks
Statistic Small Medium Large
Means – Cohen’s d 0.2 0.5 0.8
ANOVA – f 0.1 0.25 0.4
ANOVA – eta squared 0.01 0.06 0.14
Regression f-test 0.02 0.15 0.35
Correlation – r or point serial 0.1 0.3 0.5
Correlation – r squared 0.01 0.06 0.14
Association – 2 x 2 table – OR 1.5 3.5 9
Association – Chi-square – w or Phi 0.1 0.3 0.5
Source: Hunt. (n.d.). A researcher’s guide to power analysis. Utah State University. Retrieved from
https://research.usu.edu/irb/wp-
content/uploads/sites/12/2015/08/A_Researchers_Guide_to_Power_Analysis_USU.pdf
Course Project Worksheet – Calculating
Sample Sizes Using G* Power
Using the G* power website, download the free software and conduct a G* power analysis using the
provided data.
There are 4 types of power analysis (a priori, post-hoc, criterion, and sensitivity). For the purposes of this
class, we will focus on a priori power analysis since it is most commonly used when designing a research
study (Hunt, n.d.).
Using the following parameters, complete a G* power analysis:
Alpha= .05
Power= .80
Expected Effect Size = In Week 2 Discussion 2, we practiced using the “Which Stats Test” Sage Tool.
Refer to the statistical test determined using that tool and select the large effect size for the appropriate
test. (Note: if you aren’t sure which test to use, you can use the t-test family, correlation). You will not
lose points for choosing the incorrect test. The point here is to determine a test, input the
parameters into G*power, and explain the results.
Figure 1 – Effect Size Benchmarks
Statistic Small Medium Large
Means – Cohen’s d 0.2 0.5 0.8
ANOVA – f 0.1 0.25 0.4
ANOVA – eta squared 0.01 0.06 0.14
Regression f-test 0.02 0.15 0.35
Correlation – r or point serial 0.1 0.3 0.5
Correlation – r squared 0.01 0.06 0.14
Association – 2 x 2 table – OR 1.5 3.5 9
Association – Chi-square – w or Phi 0.1 0.3 0.5
Source: Hunt. (n.d.). A researcher’s guide to power analysis. Utah State University. Retrieved from
https://research.usu.edu/irb/wp-
content/uploads/sites/12/2015/08/A_Researchers_Guide_to_Power_Analysis_USU.pdf
