Hi All, I'm a marketer trying to understand the math behind A/B testing. I understand how to calculate sample size before a test is run. I've just come across a tool that estimates how many more samples are required to reach significance for a test that's underway.
Entering this data, the tool tells me that I need an estimated 45 more samples to reach significance.
I've read through the explanation of sample size in a couple of statistics books, and I'm not seeing how to calculate this. I've tried working through power equations on paper, the power.prop.test() in R and running through some calculations in Excel as well. For the life of me I'm not seeing how to calculate this. Can someone help?
Code:
Visitors Goals
Group A 152 12
Group B 150 20
I've read through the explanation of sample size in a couple of statistics books, and I'm not seeing how to calculate this. I've tried working through power equations on paper, the power.prop.test() in R and running through some calculations in Excel as well. For the life of me I'm not seeing how to calculate this. Can someone help?