Activity 4.3 Instructions Document
4.3 Power Estimation using G*Power
Power and power analysis are important concepts. Power, as defined by the textbook, is a statistical quantity that provides an indicator of how likely you will be to detect an effect from your experimental manipulations based on your experimental design and other factors. Effect size and sample size, among other things as well, are related to power.
The two ways to check the power of your design are to 1) look up previous literature that uses a similar design and see what kind of power they obtained through their efforts, or 2) use software like G*Power to estimate your power based on your methodology and experimental design.
After reading the section in your text about effect size, sample size, and power download G*Power and install it on your computer for use in this exercise and future exercises. See download link below.
G*Power is a tool to compute statistical power for many different t-tests, F tests, χ2 tests, z tests and others. G*Power can also be used to compute effect sizes and to display graphically the results of power analyses.
Download G*Power software.
Install G*Power on your computer and perform the exercise below:
4.3.1: Part I: G*Power Exercises: Estimation of Power Related Parameters Using G*Power:
1. Use G*Power to estimate the required sample size given the following test parameters:
• Type of test: t-test
• Statistical test: Means: Difference between two independent means (two groups)
• Type of power analysis: A priori: Compute required sample size – given alpha level, power, and effect size
• Tails: Two
• Effect size: Medium effect size
• Alpha level (prob): 0.05
• Power: 0.8
• Allocation ratio: 1
2. After you have input the proper parameters as outlined above, hit “calculate” to obtain your G*Power Results.
3. After you run your G*Power analysis and obtain your results, click on the “Protocol of Power Analyses” tab at the top of your G*Power window. A window will appear with your parameters and output. Select “Print” and print your G*Power output as a pdf file. Save this pdf file for upload as one of your deliverables for this exercise. Name your pdf file “4.3.1 GPower Protocol Output”.
4. 3.2: G*Power Short Answer Questions:
Using your G*Power Output “4.3.1 GPower Protocol Output”, answer the following questions related to the power analysis you just ran. Create a MSWord document and call it “4.3.2 Short Answer Questions” and save it as a deliverable for this exercise.
1. What type of statistical test did you just estimate power and sample size for?
2. What does a “medium effect size” mean and is this sufficient or this type of statistical test?
3. What does a power of 0.8 mean, and is it sufficient for this type of statistical test?
4. What does a “two-tailed test mean?
4.3.3: Write Up Your G*Power Results:
Write up your results in APA 6 format. Be sure to include the parameters of your test and an explanation of what each parameter means (type of test, statistical test, type of power analysis, tails, effect size, alpha level, power, and your calculated sample size). Write up your results and save your write up as “4.3.3 Results Write Up”.
