No matter how well written and comprehensive your programme
schedule is, there is a strong likelihood the project will not be delivered on
time. Why is that? Because every project is subject to
uncertainty.
Unfortunately, even when the original estimates are good,
and actual task durations are on average close to the original estimates, a
phenomenon called merge bias means that the more predecessors any given activity
has, the less probable it is to start on time.
Because we recognise and acknowledge this risk, every
programme we write undergoes as a matter of course, an in-depth risk analysis
using Monte Carlo simulation.
Monte Carlo simulations are used to model the probability of different outcomes in a process that cannot easily be predicted, due to the intervention of random variables. The technique was first developed by Stanislaw Ulam, a mathematician who worked on the US Atomic Bomb - Manhattan Project.
Monte Carlo simulation is a computerised process using specialist software which performs risk analysis by calculating the range of probable dates for every single activity/milestone in the project. It then identifies all potential critical paths through the project, and having done this, builds models of possible results by substituting a range of values—a probability distribution for every task in the programme schedule.
These are then calculated and recalculated 15,000 times over and over, each time using a different set of random values from the probability functions. The resulting Sensitivity Analysis then helps identify the key areas and tasks to reduce uncertainty in deliverable outcomes. The result is a programme schedule with a high confidence in accuracy of completion date.
