Three-point estimation: Difference between revisions

Revision as of 10:20, 5 August 2009

Revision as of 02:49, 6 August 2009

Line 1:

{{WikifyArticle issues|datewikify =January 2009}}{{Unreferenced|dateunreferenced =January 2009|context =March 2009|cleanup =March 2009}}

{{Context|date=March 2009}}

{{Cleanup|date=March 2009}}

The '''three-point estimation''' technique is based on statistical methods, and in particular, the [[normal distribution]]. Three-point estimation is the preferred estimation technique for [[information systems]] (IS) projects. In the three-point estimation there are three figures produced for every estimate:

Line 29 ⟶ 27:

* Confidence level in E value + 2 × SD is approximately 95%

* Confidence level in E value + 3 × SD is approximately 99.5%

* IS{{huhClarify|date=August 2009}} uses the 95% confidence level, i.e. E Value + 2 × SD, for all project and task estimates.

These confidence level estimates assume that the data from all of the tasks combine to be approximately normal (see [[Asymptotic distribution#Asymptotic normality|asymptotic normality]]). Typically, there would need to be 20–30 tasks for this to be reasonable, and each of the estimates E for the individual tasks would have to be unbiased.

Line 38 ⟶ 36:

* [[Triangular distribution]]

{{DEFAULTSORT:Three-Point Estimation}}

[[Category:Statistical approximations]]

[[de:Drei-Zeiten-Methode]]

{{Statistics-stub}}

[[de:Drei-Zeiten-Methode]]