Numerical anchors and their strong effects on software development effort estimates

• Irrelevant information may mislead project cost estimates (anchoring effect).
• Three experiments with software developers examined moderators of anchoring.
• More (less) precise numbers did not lead to a stronger (weaker) anchoring effect.
• More (less) credible sources did not lead to a stronger (weaker) anchoring effect.
• All misleading information should be removed before projects are estimated.

The anchoring effect may be described as the tendency for an initial piece of information to influence people's subsequent judgement, even when the information is irrelevant. Previous studies suggest that anchoring is an important source of inaccurate software development effort estimates. This article examines how the preciseness and credibility of anchoring information affects effort estimates. Our hypotheses were that anchors with lower numerical precision and anchor sources with lower credibility would have less impact on effort estimates. The results from three software project effort estimation experiments, with 381 software professionals, support previous findings about the relevance of anchoring effects to software effort estimation. However, we found no decrease in the anchoring effect with decreasing anchor precision or source credibility. This suggests that even implausible anchors from low-credibility sources can lead to anchoring effects, and that all kinds of misleading information potentially acting as estimation anchors in project estimation contexts should be avoided.