> As you can see, the calculations are absolutely fair and transparent.
...if you can grant them the premise that the 3.3% sampled represents the project as a whole so that the ratio will project out to 27k overall.
...if you can grant them the premise that the 3.3% sampled represents the project as a whole so that the ratio will project out to 27k overall.
That's a few million sample lines tested.
Nevertheless I agree with you: there are no obvious way to do a better estimation, so words "fair" and "transparent" seem right in place there. Of course only if Karpov does not try to mislead his readers deliberately by choosing sub projects by some criterion that correlates with error rate.