[Fomite]

If future users are markedly different than past users, a p-value isn't going to help you here.

It's not unreasonable to assume it's a sample, I just don't think it's worth getting paralyzed by worrying about whether or not you have power, or getting into hacky tricks to try to fix it.

...but most power calculations are also sort of bullshit.

[RA_Fisher]

It may be that after analyzing the data, we still have substantial uncertainty, just depends on the process’s inherent variability and what the data provides in terms of information (a function of the skill of the person determining what should be collected).