|
Quote: |
|
 |
|
|
Jerry, one thing just wonders me, why you did not take VWAP[i] in your formula, so Variance = SUMi[Pi(pi - VWAPi)2] ? This would make more sense to me. |
|
|
|
|
Ok let's give an example of computing variance:
Consider the 5 numbers, 1 2 3 4 5 all of equal weight for simplicity
what is their average: (1+2 + 3 +4 +5)/5 = 3.0
what's the variance: [(1-3.0)^2 + (2-3.0)^2 + (3-3.0)^2 + (4-3.0) ^2 + (5-3.0)^2]/5 = [4.0 +1.0 + 0 + 1.0 + 4.0]/5 = 2.0
Do you notice what value I use for the average in each of the squared terms? It's 3.0.
If I added another number to the series, say 6, then the new average would be (1 + 2 + 3 +4 +5 +6)/6 =3.5
I would then compute the next variance using this average in the squares.
Hope this clears up the computation method