Dear All,
I am embarassingly clueless regarding statistical analysis. In a few words... i need to work out an appropriate effect size for a gender comparison into coping mechanisms from a quantitative perspective. I have read.. and reread various manuals and am still struggling with this! I'm not sure of my T test or other info that i should be plugging into the G power analysis system to generate my desired sample size?? Help please from a very confused student!
Best Wishes ;-)
The effect size is the minimum effect that you want to design your study to detect. It is not the effect size that you expect.
The following is a great paper for explaining what power is: http://www.lifesci.sussex.ac.uk/home/Zoltan_Dienes/inference/Baguley_2004_Applied-Ergonomics.pdf
Suppose you are looking at some standardized test or personality measure and that the manual for the test/measure says that the standard deviation of the measure should be around 1.0. Suppose that you want to be able to detect of difference of about half of this. This would be what you would use. Jacob Cohen's A Power Primer is useful (google it and you'll find a copy) as it provide tables that might be easier to use than G*Power.
Daniel,
Thank you so much for the taking the time to reply. I will look at this paper.
Best Wishes
Ruth
The Handbook of Biological Statistics might be useful. It does use G-power, and is overall pretty easy to understand.
Power analysis general:
http://www.biostathandbook.com/power.html
G-power for t-test:
http://www.biostathandbook.com/twosamplettest.html
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Statistical Software
- R Statistical Package