• We are pleased to announce that the winner of our Feedback Prize Draw for the Winter 2024-25 session and winning £150 of gift vouchers is Zhao Liang Tay. Congratulations to Zhao Liang. If you fancy winning £150 worth of gift vouchers (from a major UK store) for the Summer 2025 exam sitting for just a few minutes of your time throughout the session, please see our website at https://www.acted.co.uk/further-info.html?pat=feedback#feedback-prize for more information on how you can make sure your name is included in the draw at the end of the session.
  • Please be advised that the SP1, SP5 and SP7 X1 deadline is the 14th July and not the 17th June as first stated. Please accept out apologies for any confusion caused.

variance confusion

N

nicolathompson

Member
Hi,

I'm confused about the equations for variance.

We have:
var(X+Y) = var(X) + var(Y) if X and Y independent
var(nX) = (n^2)var(X)


But in chapter 7 compound distributions:
S= X1 + X2 + ... + XN
var(S given N=n) = nvar(X) WHY NOT (n^2)var(X)?
For example, say n=3. Then since all Xs are iid rvs, isn't var(S given N=3) just
var(X+X+X) = var(3X) = 9var(X)?
 
Var(X+Y) = Var(X) + Var(Y) if X,Y independant.
If considering X1,X2,X3..XN which are different observations of independant (and indentical) distributions, it's like above.
Var(X1+X2+X3+...+XN) = Var(X1)+Var(X2)+Var(X3)+...Var(XN)
= nVar(X) since all var are the same

Note if considering Var(n*X), VAR(nX) = (n^2)Var(X)
Difference here is you take one observation and multiply it by n.
Note that one observation is obviously dependant on itself (above formula not valid).

Say you flip a coin, X~Bin(1,0.5)
and n=3.
The first is where you flip 3 coins and add the number of heads together, giving you a Bin(3,0.5)
The second is you flip one coin and multiply by 3, so you get 3*0 with probabilty of 0.5, and 3*1 with probability of 0.5. (Can't get 1,2)
 
just thinking bout this

Something that perhaps adds to the confusion is that .

Here you are considering the distribution of sigma( Xi ) , but when we think about the distribution of X bar the 1/n factor does the usual and gets squared so the variance goes from being n(sigma squared) to (sigma squared)/n.
 
Back
Top