Prev: Radial Bases Function Networks with K means
Next: Question on the derivate /calculus of a 2-norm matrix . Thanks a lot
From: shahnaz fatima on 25 Jul 2010 09:06 what is n times variance called where n is total number of samples. nxσ2 until recently i remembered . it starts with letter s .can anybody reply for me plz
From: dpb on 25 Jul 2010 10:00 shahnaz fatima wrote: > what is n times variance called where n is total number of samples. > nxσ2 > > until recently i remembered . it starts with letter s .can anybody reply > for me plz You mean sum of squares? Of course, variance is normally considered the unbiased (n-1) divisor instead of n so there would be the n/(n-1) thing to account for in that case...but, not sure if that's the question absolutely. Context for the desired result might help overcome the language hurdle... --
From: TideMan on 26 Jul 2010 00:31
On Jul 26, 2:00 am, dpb <n...(a)non.net> wrote: > shahnaz fatima wrote: > > what is n times variance called where n is total number of samples. > > nxσ2 > > > until recently i remembered . it starts with letter s .can anybody reply > > for me plz > > You mean sum of squares? Of course, variance is normally considered the > unbiased (n-1) divisor instead of n so there would be the n/(n-1) thing > to account for in that case...but, not sure if that's the question > absolutely. > > Context for the desired result might help overcome the language hurdle... > > -- Another option is that the OP is totally screwed up and what he/she is looking for is: Standard Error = sqrt(variance/n) |