(1) Construct or describe a probabilistic process.

For the random nature of wood, such as particle transport, it is mainly to describe and simulate this probability process correctly. For deterministic problems with non-random properties, such as calculating definite integral, it is necessary to construct an artificial almost-seating process in advance, and some of its parameters are the solutions of the required problems. In other words, a non-random problem should be transformed into a random problem.

(2) sampling from known probability distribution is realized.

After constructing probability models, all kinds of probability models can be regarded as composed of various probability distributions, so generating random variables (or random vectors) with known probability distributions has become the basic means to realize Monte Carlo simulation experiments, which is why Monte Carlo method is called random sampling. The simplest, most basic and most important probability distribution is the uniform distribution (or rectangular distribution) on (0. 1).

(3) establish various estimators

Generally speaking, after constructing the probability model and sampling from it, that is, after realizing the simulation experiment, a random variable must be determined as the solution of the required problem, which we call unbiased estimation. Establishing various estimators is equivalent to investigating and registering the results of simulation experiments, from which the solution of the problem can be obtained.