PMI and Capella Together – Read More

Monte Carlo Simulation

The Monte Carlo Simulation document is an early access document and is to be used for basic Monte Carlo simulation of normal or lognormal distributions only. This will be developed over time based on user feedback.

We recommend that you use verified software for more complex simulations.

Open the named file, and the Introduction input sheet will be presented. The document contains instructions as needed.

The simulation is completed on the Simulator tab.

Figure 1 – Simulator tab

Each column is an input (X) to be simulated. This is to be used when you want to simulate random variables to use as process inputs to then calculate a predicted response (Y).

For each column, complete the following:

  • Simulate? – this indicates whether you want to simulate another X. Selecting Yes from the drop-down box will then generate simulated data below for that column.
  • Distribution – select a probability distribution to be used for the data. Currently, this document simulates only Normal or Lognormal distributions.
  • Mean – enter a known mean for X. This should be known from previous analysis or information. In Lognormal distributions, this is where you enter Location instead of mean.
  • SD – enter a known standard deviation for X. This should be known from previous analysis or information. In Lognormal distributions, this is where you enter Scale instead of SD.
  • Coefficient –  this is optional – enter a known coefficient for X from previous analysis or information. This can often come from a regression equation. This is for when you have an underlying equation to use for prediction. Otherwise, leave this blank.

Simulated results using this information then appear in the inputs section below. 

Figure 2 – Simulated Y

Scrolling to the right will then display 2 sets of response data. These are the simulated results using the simulated X inputs.

There are 2 sets of responses, but only 1 is to be used for your analysis:

  1. Response using equation – use this when you are using a prediction equation (with coefficients) to predict the response. This will often come from previous regression analysis for example.
  2. Response using SUM – use this when you are not using an equation and are predicting process timings. This simply adds all simulated inputs together.



Join our LinkedIn Network

Keep up to date with all the latest performance improvement resources to inform and inspire as you continue to grow.

Follow PMI on LinkedIn