p1: Most non-financial ML researchers can assume that observations are drawn from IID processes. You can obtain blood samples from a large number of patients, and measure their cholesterol. Of course, various underlying common factors will shift the mean and standard deviation of the cholesterol distribution, but the samples are still independent. p2: A first solution is to drop overlapping outcomes before performing the bootstrap. Because overlaps are not perfect, dropping an observation just because there is a partial overlap will result in an extreme loss of information. I do not advise you to follow this solution.

In regard to average scores in outdoor golf, participants reporting “I don’t know” comprised 41.1% (n = 160) of the total sample, followed by greater than 100 (n = 74, 19.0%), between 91 and 99 (n = 73, 18.8%), between 82 and 90 (n = 58, 14.9%), and less than 81 (n = 24, 6.2%). Additionally, in terms of average scores in virtual golf, participants reporting “I don’t know” comprised 48.6% (n = 189) of the total sample, followed by between 82 and 90 (n = 63, 16.2%), greater than 100 (n = 50, 12.9%),