I am about to evaluate the outlier detection mode of random forests. At [1]stat.berkeley.edu/~breiman/RandomForests/cc_home.htm#outliers the raw outlier measure for a case n is defined as nsample/AverageProximity I wasn't able to figure out, what "nsample" stands for. Can anyone help me? References 1. stat.berkeley.edu/~breiman/RandomForests/cc_home.htm#outliers