**Pros and Cons**

Simulation technique allows experimentation with a model of the real life system. Whenever experimenting with the system itself is risky and/or costly, simulation helps in forming a fair idea of the outcome of changes in certain variables. Usually, after constructing the model of a system, one or more input variables are varied for each successive experiment. This would help in the recognition of the major parameters governing the system and proper measures can be taken to improve the overall performance of the system.

Simplifications and assumptions usually required in analytical approaches, are not required for simulation. Hence, managers can easily understand and appreciate simulation. Simulations can also be used to break down complex systems into sub-systems and study the behavior of each of these sub-systems individually or jointly with other sub-systems.

Another advantage of the simulation approach is its flexibility. Extremely complex systems with uncertainty can be studied with a reasonable degree of accuracy. Note that reliability of the results - whether from simulation or analytical approach - depends crucially on how well the mathematical model represents the real system.

The main disadvantage of simulation is that it is very computer-intensive. Large blocks of expensive computer time may be necessary even for a relatively simple problem. This is particularly true when a large number of runs are required to ensure a reasonable degree of accuracy.

Another drawback is that it does not produce optimal solutions. As the number of parameters increases, the difficulty in finding the optimum values increases to a great extent.

Finally, in terms of information requirements to formulate a reasonable model, the simulation approach is not very different from the analytical approach. While uncertainty can be built into a simulation model, most of the times a simplistic model may be used.

The simulation approach has found extensive applications in the area of business decision making. Some examples are, investment appraisal under uncertainty, analysis of performance of portfolios, waiting line problems, corporate financial models, corporate planning, inventory decisions, etc. Any complex system about which the investigator has sufficient knowledge in terms of interrelationship of variables can be tackled with this approach.