Every project manager will have that occasional project where they’ve overshot the deadline, despite their best efforts.
Why is this so common?
You may plan well, but because things rarely happen according to plan, you may be forced to deviate from the original estimates. Consequently, your projects don’t meet their delivery dates or budgeted cost exceed the actual cost.
So how can you reduce the chances of this happening? The key is proper risk analysis during the project planning phase. A Monte Carlo simulation allows you to assess the impact of risk and make realistic project estimates where time and budget are concerned.
Let’s learn more about the Monte Carlo method, its benefits, limitations, and how to incorporate it into your project planning and management.
What is the Monte Carlo Method?
The Monte Carlo simulation is a method used by project managers to analyze the impact of risks on their projects. It helps managers play out the scenario in which risk occurs and assess how it would affect the schedule or the project’s cost. This method provides you with a range of possible outcomes and probabilities to fully understand the impact of risk and uncertainty.
A Monte Carlo simulation, also referred to as multiple probability simulation, can help project managers tackle various problems in virtually every field, including but not limited to construction, medical, engineering, IT, finance, supply chain, and science.
This simulation technique was first developed in 1940 by Stanislaw Ulam, a mathematician. It borrows its name from the popular gambling destination in Monaco, where chance and random outcomes are central to the games, just as they are to this method.
How the Monte Carlo Simulation Method Works
The Monte Carlo simulation assumes that you can’t determine the probability of varying outcomes due to interference from random variables. The method hence focuses on constantly repeating random samples to achieve specific results.
When running a Monte Carlo simulation, you take the variable with uncertainty and assign it a random value. Then you calculate the results over and over, each time using a different set of random values from the probability functions.
You could make thousands or tens of thousands of recalculations before you complete a simulation. Once you complete a simulation, average the results together to get an estimate.
Let’s use an example to make things more straightforward.
You’re creating your project plan and want to create a timeline for all the tasks involved. You come up with the best-case scenario and the worst-case scenario. Assuming everything aligns with your plan and there are no delays in completing all tasks and deliverables, you’ll deliver the project in 12 months.
However, if delays occur, you assume that the project completion time will increase to 15 months. With these two scenarios, you can use the Monte Carlo technique to analyze all the potential combinations and quantify your project completion estimates:
- Probablity of completing the project in 12 months is 15%
- Probablity of completing the project in 13 months is 50%
- Probability of completing the project in 14 months is 80%
- Probablity of completing the project in 15 months is 100%
A Monte Carlo Analysis uses probability distribution (a model of possible values) to describe uncertainty when conducting a risk analysis.
Common probability distributions include:
- Normal: Also referred to as a “bell curve.” In this distribution, the project manager simply defines the mean (expected) value and a standard deviation to describe the variation in the mean. The normal distribution is symmetric and describes various natural phenomena such as people’s heights, inflation rates, etc.
- Lognormal: This type of distribution has positively skewed values, unlike the symmetric values of a normal distribution. It represents values that don’t fall below zero but have unlimited positive potential. Such variables include stock prices, real estate property values, oil reserves, etc.
- Uniform: All values have an equal probability of occurring in this distribution. The project manager simply defines the minimum and maximum. Uniform variables can include manufacturing costs or future sales revenues for a new product.
- Triangular: Here, you define the minimum, most likely, and maximum values. The most likely values are the ones more likely to occur. Variables in this distribution can be past sales history per unit of time and inventory levels.
- Discrete: Here, you define specific values that may occur and the likelihood of each. A good example is the results of a lawsuit: 20% chance of a favorable verdict, 30% chance of an unfavorable ruling, 40% chance of settlement, and 10% chance of mistrial.
Benefits of the Monte Carlo Technique in Project Management
There are a number of benefits of using a Monte Carlo analysis on your projects. A few include:
- You get to see how likely you are to meet project milestones and deadlines early in the planning phase.
- It helps you create a more realistic budget and project schedule.
- It’s possible to predict the chances of schedule and cost overruns occurring.
- When you quantify risks, you can quickly assess the impacts.
- Your decisions are based on objective and insightful data.
- Quickly create graphs of the different outcomes and their chances of occurrence and use them to communicate findings to other stakeholders.
Limitations of the Monte Carlo Technique in Project Management
You’re also likely to face some challenges while using the Monte Carlo analysis, such as:
- Your simulation must contain three estimates ( most likely duration, the worst-case scenario, and the best-case scenario) for every activity or factor being analyzed.
- Your analysis will only be as good as the estimates you provide.
- You only see the overall probability for the entire project or a phase, not individual activities or risks.
Monte Carlo Simulation in Project Management
Research shows that 28% of the projects fail due to incorrect project estimates. It’s, therefore, crucial for project managers to create an accurate forecast.
To get appropriate estimates, you must consider all the unexpected events that might disrupt the project. In other words, you must do your risk analysis during the planning phase to identify the weaknesses, strengths, and possible opportunities during or after completing a project.
The Monte Carlo simulation is a data-driven approach that helps project managers to quantify and understand project risks and predict outcomes.
Using a project management tool such as Mission Control can help you collect data-driven and precise estimates for your simulations. The risk log is a reliable way to track potential risks that can negatively impact your project. This log will help you pick out the uncertainties in your project and create the best-case, and worst-case scenarios should the risks occur.
Use our Gantt chart feature to schedule, assign and monitor project tasks with complete visibility. This chart can help you identify bottlenecks you can use as variables in your Monte Carlo simulation.
A Kanban board is also a great feature to organize your project activities. The graphical view of the Kanban allows you to identify and prioritize your risks if they exist.
Contact us today for a demo of how Mission Control can help your organization carry out effective risk analysis and plan projects better.
