Subjective Time Estimates in Critical Path Planning--A Preliminary Analysis

A historical analysis of activity time estimates made by a number of contractors on a large-scale systems development project is conducted using two basic hypotheses. (1) Pre-activity time estimating accuracy improves as the beginning date of the activity approaches. (2) Time estimates made during the progress of an activity improve in relative accuracy as the completion date of the activity approaches. These hypotheses are tested and several models for adjusting time estimates on the basis of the estimator's past history are developed and tested. The results are not proposed to be definitive--but rather, preliminary ones which should serve to demonstrate the feasibility of the basic approach.