Q: What do I need to do to ensure my simulation results are reproducible?
A: The results of a simulation should be reproducible from simulation to simulation if
- You use the same, fixed random number generator seed. This can be set in the Sampling tab of the Simulation Settings dialog. For reproducible results, make sure this value is greater than zero.
- Your model has not be changed between simulations.
- You have not used functions in your spreadsheet that generate random numbers outside of @RISK's control. Excel's RAND() function is the most common example of this type of function. The numbers generated by RAND() are controlled by Excel, which uses its own independent random number stream.
- You have not used functions that change depending on when the model is run, such as Excel's TIME() function.
- You avoid running macros or custom VBA function that do not exactly reproduce their results from simulation to simulation.