| Type: | Package |
| Title: | Jackknife Mutual Information |
| Version: | 0.1.0 |
| Author: | Zeng Xianli <a0123862@u.nus.edu>, Hang Weiqiang <e0010758@u.nus.edu> |
| Maintainer: | Zeng Xianli <a0123862@u.nus.edu> |
| Description: | Computes the Jackknife Mutual Information (JMI) between two random vectors and provides the p-value for dependence tests. See Zeng, X., Xia, Y. and Tong, H. (2018) <doi:10.1073/pnas.1715593115>. |
| License: | GPL-2 |GPL-3 [expanded from: GPL (≥ 2)] |
| Encoding: | UTF-8 |
| LazyData: | true |
| Imports: | Rcpp |
| LinkingTo: | Rcpp, RcppArmadillo |
| RoxygenNote: | 6.0.1 |
| NeedsCompilation: | yes |
| Packaged: | 2018-10-15 08:00:58 UTC; weiqianghang |
| Repository: | CRAN |
| Date/Publication: | 2018-10-19 15:10:12 UTC |
Jackknife Mutual Information
Description
This function provides method for dependence test. It uses permutation test to determinethe rejection region.
Usage
JMI(x, y, BN = 1000)Arguments
x | n by p sample matrix. |
y | n by q sample matrix. |
BN | Number of permutations, the default value is 1000. |
Value
the output is a list which contains:
mi: the value of Jackknife Mutual information
pvalue: the p-value of independence test that based on the permutation of JMI, the value is not provided if BN=0.
References
Zeng, X., Xia, Y., & Tong, H. (2018). Jackknife approach to the estimation of mutual information[J]. Proceedings of the National Academy of Sciences, 201715593.
Examples
x <- matrix(rnorm(50*3),50,3) y <- matrix(rnorm(50*2),50,2) #calculate the Jackknife Mutual information between x and y. JMI(x,y,0)$mi #calculate the p-value of independent test between x and y that based on 500 permutations. JMI(x,y,500)$pvalue