Let's say I have the following dataset of downloads per day grouped per week.
week1: 1 0 0 0 1 0 0
week2: 2 0 2 0 0 2 0
Now I want to know whether the downloads in week1 are significantly different compared to week2. Which statistical test do I apply? Poisson, randomization-test or something else?
I tried a randomization test of 10k iterations. The p-value is about: 0.17. The t-test is 0.2326. Now I think somehow Poisson should model it better, but I don't know how to do it.