This forum includes discussion about project risk analysis and risk management theory: Monte Carlo simulations, Event Chain Methodology, schedule and cost risk analysis. Please submit questions and case studies about your experience with our project risk analysis software.
Moderator: Intaver Support
- Posts: 10
- Joined: Wed May 28, 2008 4:05 am
I'm running 1000 simulations for project in my project schedule. It is enough?
- Posts: 912
- Joined: Wed Nov 09, 2005 9:55 am
It depends on schedule. In most real life projects 600 - 800 iterations will give very accurate results. Remember that accuracy of analysis should correspond with accuracy of input data. Input probability and outcome of risks as well as uncertainties, defined by statistical distribution of task duration and cost are not fully accurate and reliable. It is still our assessment. Sometimes this assessment relies on historical data, sometimes it is based on expert option. However after approximately 600 - 800 iterations results of analysis (e.g. mean and statistical deviation of project duration and cost) start to converge. In other words difference in mean and statistical deviation of project duration and cost on current and previous iterations will be only few percent. It means that additional iterations will not increase accuracy of analysis. However there are few exceptions. One of them is rare events with probability less then 1%. In schedules with such rare events you would need number of iterations because otherwise such event will never occur during a course of simulations.
Intaver Support Team
Intaver Institute Inc.
Home of Project Risk Management and Project Risk Analysis software RiskyProject