Yesterday, the City of Ottawa's Mayor Jim Watson announced that the Light Rail Project is going ahead at a projected cost of $2.1 Billion. This came as a relief to the people who were certain it would be more than double that, especially taxpayers who would be footing the bill.
It nearly goes without saying that no one, especially not the local media, asked the obvious questions "What's the probability of meeting or beating the projection?" "Is the 2.1 billion a maximum, a minimum, what?"
A little Probability Management is in order. First, the 2.1 billion is at best a minimum. If all goes exactly as planned, the contractors will present a bill for $2.1 billion. They aren't going to leave any money on the table. Second, if anything goes wrong, as it surely will, the bill will be higher. Given the history of infrastructure projects in Canada, the cost probability distribution looks something like this:
This is a pretty fair representation of these kinds of projects--from never less to sometimes eight or ten times the original estimate.
In this case, the "heads it's over, tails it's under" bet is $5 Billion.