Reducing the risk of software cost estimation

Inaccurate cost estimation is a well-known problem in software development. The common cost estimation models are point estimates that are unable to quantify uncertainties. Furthermore, it is difficult to calibrate the uncertainties in cost estimation due to the lack of information. The purpose of this thesis is to prove that probability techniques could be synthesized into COCOMO (Constructive Cost Model) to quantify uncertainties. Another aim is to find out how to get more insight on reducing the risk of cost estimation. In this thesis, some historical data is presented to show the variance in factors of COCOMO. Monte Carlo simulation method is also introduced into COCOMO to quantify the uncertainties. Finally, a “What-if\u27 study is facilitated to find the potential factor changes to affect the result of simulation. The result of the study reveals that process maturity has more influence than productivity on reducing variance of estimation. It indicates that synthesizing Monte Carlo simulation and “What-if\u27 studies into COCOMO could produce insightful information to reduce the risk of software cost estimation