Modeling Dependencies
Publisher Summary
For many applications, one needs random variates that are dependent in a predetermined way. The first aim is to generate a matrix X of size N × p. The most-used measure of dependence is linear correlation. Assume two random variables Y and Z. Then for a sample of N paired observations (y1, z1), (y2, z2), . . . , (yN, zN) linear correlation ρ is computed. Markov chains is another model of dependence. This approach is particularly useful for time series with conditional probabilities, and Markov chain Monte Carlo plays a very prominent role in financial simulations. In its simplest version, there is only a limited set of alternatives, and the probabilities for the next state of a variable only ...
Get Numerical Methods and Optimization in Finance now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
