Description Usage Arguments Value Examples
Computes the sensitity of a Tweedie Bayesian network induced by a modification of the coefficient matrix. This sensistivity relies on the Kulback-Liebler divergence between the joint probability distributions induced by the original and the modified Tweedie bayesian networks.
1 |
beta |
a lower triangular matrix of the Tweedie Bayesian network coefficients. |
phi |
a vector of dispersion parameters. |
p |
a vector of power parameters. |
db |
an upper-triangular matrix of coefficients modification. |
X |
a data frame containing the variables of the model. |
This function returns a double corresponding to the Tweedie Bayesian network sensitivity.
1 2 3 4 5 6 7 8 9 10 11 12 | ## Not run:
beta = matrix(0,ncol=5,nrow=5)
beta[1,1] = 1;
beta[2,1] = 0.5
beta[3,1] = -0.5; beta[3,2] = -0.7;beta[3,3] = -1.2
beta[4,1] = -2; beta[4,3] = -1
beta[5,1] = 0.2; beta[5,4] = 1; beta[5,5] = -2
db = matrix(0,ncol=5,nrow=5)
db[2,2] = 0.1 # adding an arc from X1 to X2.
sensi.tbn(beta, c(1,2,1.5,1,1), c(2,2,3,2,0), db, X)
## End(Not run)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.