About Monte Carlo Simulation and Simulation Accuracy

Strategic Modeling uses Monte Carlo simulation to randomly generate a range of values for assumptions that you define.

After you've defined input cells as assumptions and output cells as forecasts, you run a simulation. Strategic Modeling uses Monte Carlo simulation, which uses random numbers to measure the effects of uncertainty in a model.

A simulation iteratively performs these steps:

1. For every assumption cell, a random number is generated according to the range you defined and is placed in the model.

   Strategic Modeling generates random numbers using the Multiplicative Congruential Generator method.

2. The model is recalculated.
3. A value is retrieved from every forecast cell and added to the chart in the forecast results area.

This is an iterative process that continues until either the number of trials is reached or you stop the simulation.

The final forecast chart reflects the combined uncertainty of the assumption cells on the forecast cells.

The accuracy of the simulation is primarily governed by two factors:

• The number of trials, or length, of the simulation―Generally speaking, the more trials you run in a simulation, the greater the accuracy of the statistics and percentiles information. For a given number of trials, the accuracy of the statistics and percentiles greatly depends on the shape and nature of the forecast distribution.
• The sampling method―Monte Carlo sampling generates natural, "what-if" type scenarios while Latin Hypercube’s sampling is constrained, but more accurate.