When making any decision, risk analysis is an extremely important issue in the face of uncertainty, ambiguity and variability. Even with unprecedented information, we are still unable to predict the future with precision. Monte Carlo Simulation makes you able to master any possible outcome of a decision, assess the impact of risk, and make the best decision in the face of uncertainty.
What is the Monte Carlo simulation method?
The Monte Carlo simulation method was first used by scientists in the development of atomic bombs in the Second World War. It is a computer experiment of stochastic simulation. The problem solved is matched with the probability model and the approximate solution of the problem is obtained through a large number of computer numerical operations. This technology has been widely used in many fields such as finance, insurance, project management, energy and environment, transportation, manufacturing, engineering research and computational physics. It provides the range of possible outcomes and their probability values for any decision-making by decision makers, showing the likelihood of the most extreme events-the highest risk and the most conservative cases-and even the decision results of various median values, as a basis for risk analysis and decision-making.
How to use Monte Carlo simulation?
When a prediction model, such as linear regression, is established, known variables need to be entered to predict the results. But in reality, the input variables are often unknown items that can not be grasped. For a model for calculating profit with cost expense as its input variable, if you want to calculate whether the future profit value (with unknown cost expense) will fall below the expected target, you can use SPSS Statistics Monte Carlo simulation analysis to perform a risk analysis of cost control.
- Adapting unknown input variables to appropriate probability assignments (e.g. Gamma assignments)
- Using adaptive probability assignment to random Generation of input variable values
- Substituting the input variable value generated by simulation into the prediction model to calculate the target value of the result
- Repeating the above three steps in large numbers (usually thousands or tens of thousands of times)
Finally, the probability distribution function of the target variable can be calculated, so that the characteristics of the target variable can be understood and the risk analysis can be carried out.