Random number generation and quasi-Monte Carlo methods
Random number generation and quasi-Monte Carlo methods
Hi-index | 0.00 |
This paper discusses European style option pricing for both path dependent and nonpath dependent cases where the log returns of the underlying asset follow the normal inverse Gaussian (NIG) distributions. The moment matching method is used in estimating model parameters. The Monte Carlo method and the Sobol' sequence based quasi-Monte Carlo method combined with some variance reduction methods are used in simulating option prices. Our test results show that the (randomized) quasi-Monte Carlo method is more efficient than the Monte Carlo method if both with the same variance reduction method.