Kernel Density Estimator for the Mutual Information
| advisor: | Dr. Georges Darbellay |
| e-mail: | show e-mail |
| type: | bachelor thesis, master thesis |
| branch of study: | MI_MM, II_SIMI |
| key words: | Density estimators, Statistics, Finantial time series, Information |
| description: | The mutual information is a measure of the dependence between two random variables. In many ways it has better properties than the widely used coefficient of linear correlation. In this project we are interested in analysing statistical dependences in finantial time series. To estimate the mutual information from data it is necessary to construct an estimator. Our goal will be to develop a multivariate kernel density estimator, test it on some examples for which the mutual information is known analytically, and apply it to data from the financial markets. This work includes some programming since we are dealing with data. |
| last update: | 20.11.2017 22:16:51 |
administrator for this page:
Ľubomíra Dvořáková | last update: 09/12/2011