oooh, don’t get me started on expectation values… I have heated opinions here, sorry. The two easiest problems with expectations in this case is that to average something, you need to average over some known space, according to some chosen measure—neither of which will be by any means obvious in a real-world scenario. More subtly, with real-world distributions, expectation values can often be infinite or undefined, and median might be more representative—but then should you look at mean, median, or what else?
oooh, don’t get me started on expectation values… I have heated opinions here, sorry. The two easiest problems with expectations in this case is that to average something, you need to average over some known space, according to some chosen measure—neither of which will be by any means obvious in a real-world scenario. More subtly, with real-world distributions, expectation values can often be infinite or undefined, and median might be more representative—but then should you look at mean, median, or what else?