Performance Tracking with Event and Event Chains
Monitoring the activity’s progress ensures that updated information is used to perform the analysis. During the course of the project, the probability and time of the events can be recalculated based on actual data. Quantitative analysis can be performed again and a new project schedule and cost will be generated. The main issue with performance tracking is forecasting an activity’s duration and cost if an activity is partially completed and certain events are assigned to the activity. The simple heuristic approach to this problem is to analyze the moment of risk, which is defined as one of the event parameters. If the moment of risk is earlier than the date when actual measurement is performed, this event will not affect the activity.
This main concern with this approach is whether it takes into consideration risks that have already occurred before the measurement. For example, the risk “Problem with testing equipment” can occur during the course of the activity “System Design” with a probability 50%. For example, what will occur if this risk has already occurred twice by the time the activity is 50% completed? What will be the probability of this risk occurrence during second half of the activity?
Using actual performance data original estimate to forecast duration of activity with risks
The solution can be found by performing an analysis of the historical data that is augmented with actual tracking data using a Bayesian approach where