Talk:Three-point estimation

riddled with typos.
Typos everywhere. That is all [dated 20 May 2013]

Factually incorrect
"Confidence level in E value +/- SD is approximately 68%... etc" Technically, what is being referred to here is not the 'confidence level in E', the following is also technically incorrect: "Calculates the SD value for the total project work as SD (Project Work) = √(Σ SD (Task) 2)"

In the first case, the SD referred to {"SD = (b − a) / 6"} is the SD of the triangular distribution not the the standard error of the mean (which is unknown in this example). In the second case, this summation only works if all tasks times are independent, identically distributed, and normally distributed - plainly not often the case, otherwise you wouldn't be using 3pt estimates.

Needs updating. [dated 20 May 2013]

Sum of standard deviations
The formula $$ \operatorname{SD}(\text{project}) = \sqrt{\sum{\operatorname{SD}(\text{task})^2}}$$ makes no sense; square root of a square is the value itself: $$\sqrt{\sum{\operatorname{SD}(\text{task})^2}} = \sum{\operatorname{SD}(\text{task})}$$. It's probably supposed to be the root mean square: $$\operatorname{SD}(\text{project}) = \sqrt{{1 \over n} \left( \operatorname{SD}(\text{task}_1)^2 + \operatorname{SD}(\text{task}_2)^2 + \cdots + \operatorname{SD}(\text{task}_n)^2 \right) }$$ 91.153.55.81 (talk) 21:44, 25 September 2022 (UTC)