Hi there Talk Stats Community,

I am an undergraduate research assistant. Currently I am doing research on a project, and our results have indicated something that is quite different from previous findings.

We have used a more specific and sensitive test to prove that a particular microbe is not responsible for causing an infection.

We believe that previous studies have found positive evidence of the microbe due to contamination.

I would like to investigate the power of our study as compared to the other studies.

The metrics of comparison are the rate of true positives (sensitivity), and the rate of true negatives (specificity). However, our study has a different sample size (number of cultures investigated) than previous studied. Does this mean that I need to use a metric that adjusts for the difference in sample number?

Can I do this by measuring the power or effect size and comparing them? If so, what measurements will I use and how can I conduct this test in R? Specifically, what is the h value that I will enter into R?

Thank you for your help and responses. Talk soon,

Marcus