25/05/2017

# 英国论文代写：MC计算方法

A broad class of computational algorithm that is dependent upon repeated processes of random sampling with an aim to acquire numerical results is known as Monte Carlo (MC) method. This technique is widely used in physics and mathematics in the cases when it is extremely hard to use any other mathematical technique. Application of Mote Carlo is of prime importance in three different problem classes that are of distinct nature namely: optimization, numerical integration, and generation of probability distributions. Many coupled degrees of freedom are associated with Monte Carlo simulation metgods in the field of physics. The fields of fluid, strongly coupled solids, disordered material and cellular structures are highly dependant upon Monte Carlo simulation methods.
In other fields of sciences when it is hard to model a phenomenon by applying traditional modeling techniques it is preferred to rely on Monte Carlo simulation. When there is huge uncertainty existing in the inputs the MC method is of significant importance. Such uncertainties are very common in calculation of business risk, evaluation of definite integrals, and solution of complicated boundary conditions. Predictions of failure are also done in the field of space and oil exploration problems and costs overruns on the basis of Monte Carlo Simulation and it has been observed that this technique remains successful in making accurate predictions (Doucet et al, 2001).
The modern version of this technique was invented in the year 1940 by Stanislaw Ulam in the time when he was working on the project of nuclear weapons. Immediately after the breakthrough the importance of the program invented by Monte Carlo was realized by the major scientists all over the world.
The log normal distribution is expressed by an output data that provides a positively skewed figure as a result of scatter plot. An important property of the distribution is that no value of less than zero is assumed by the distribution. Following are the results of Monte Carlo Simulation for a log normal distribution of stock returns. The result is obtained by using 1000 paths.