NORSYS SOFTWARE © 2012 |
NETICA API |
C VERSION 5.04 |

double GetTestQuadraticLoss_bn ( | tester_bn* test, node_bn* node ) |

Returns the "quadratic loss" of node under the tests previously performed.

The "quadratic loss" (also known as "Brier score") is defined as: **MOAC [1 - 2 * p _{c} + sum[j=1 to n] (p_{j}^{2})]**

where **MOAC** stands for the mean (average) over all cases (i.e., all cases

for which the case file provides a value for the node in question),

where **p _{c}** is the probability predicted for the state that turns out to be correct,

where **p _{j}** is the probability predicted for state j, and

where **n** is the number of states of the node.

Values for quadratic loss vary from 0 to 2, with 0 being a perfect score.

node is required to have been in the test_nodes list originally passed to NewNetTester_bn.

Version:

Versions 2.08 and later have this function.

See also:

GetTestConfusion_bn | Get elements of the confusion matrix | |

GetTestErrorRate_bn | Get the fraction of test cases for which the prediction failed | |

GetTestLogLoss_bn | Get the "logarithmic loss" score of the test | |

NewNetTester_bn | Construct the tester_bn object |