Testing Year over Year Revenue Growth between two groups?

#1
Seeking advice on the following (I am a beginner with Stats):

We have a Treated Group and a Control Group both of which have YoY growth results. What technique should we use to test for significance in the difference of the two rates?

As a further example:
Group A generated $100 in 2017 and $120 in 2018. A YoY growth of 20%.
Group B generated $100 in 2017 and $105 in 2018. A YoY growth of 5%.

The data is available at its most granular. (single purchase events by individual group members).

How do we test for significance between the 20% and the 5%?

Thanks much in advance!
-MDG
 
#2
Get the YoY growth of each individual in each group. Then use that to get the mean and standard deviation for the two groups. Conduct a 2-Sample t-test and make an inference. The following website will do the calculations. You need to come up with an alpha before running the test. Alpha is the acceptable risk in making a wrong inference. Many people will use .05, meaning they accept the risk that 5% of the time they determine there is a difference in the two groups when there actually is not.


https://www.graphpad.com/quickcalcs/ttest1/?Format=SD
 
#3
Thanks for this!
Assuming I don't have significance, what is the best method to use in order to calculate the proper control group size?
We would use an alpha of .10 (marketing not being a life-saving discipline as we practice it...)
Thanks again!