On Sunday, May 3, 2020 at 12:19:52 AM UTC-6, Brent wrote: > > > > On 5/2/2020 10:50 PM, Alan Grayson wrote: > > You mean to experimentally estimate it from the scatter of results? That >> depends on how accurately you want to estimate. The error scales as >> 1/sqrt(N). In most experiments with photons or electrons, it's easy to >> make N big. But it's also hard to eliminate other sources of scatter that >> have nothing to do with the UP. So only experiments deliberately designed >> for maximum precision are going to push the UP bounds for simultaneous >> measurements. >> >> Brent >> > > If the experiment is designed for max precision, how large does N have to > be to satisfy the UP? TIA, AG > > > That doesn't quite make sense. It takes two to get an estimate of the > variance and the first two you measure may satisfy the UP or they may > violate the NP. The variance, and the std deviation estimators are random > variables, obey a certain distribution. The bigger N the tighter the > estimate. In almost all experiments there will be other sources of > randomness and the estimate will converge around some uncertainty bigger > than h, which is satisfying the UP. > > Brent >
What is NP? If sample size doesn't satisfy the UP, how large must N be? AG -- You received this message because you are subscribed to the Google Groups "Everything List" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/everything-list/79d61004-9e45-425d-985c-e2e17a57af21%40googlegroups.com.
