java.lang.Object
riso.distributions.AbstractDistribution
riso.distributions.Noninformative
- All Implemented Interfaces:
- ConditionalDistribution, Distribution, java.io.Serializable
- public class Noninformative
- extends AbstractDistribution
An item of this class represents a ``noninformative'' lambda
message or lambda function, that is, one for a variable which is
not evidence and for which there is no downstream evidence.
|
Method Summary |
double[] |
effective_support(double epsilon)
The support for a noninformative lambda or lambda message is unbounded. |
double |
p(double[] x)
Computes the density at the point x. |
| Methods inherited from class riso.distributions.AbstractDistribution |
cdf, clone, expected_value, format_string, get_density, get_nstates, initial_mix, log_p, log_prior, ndimensions_child, ndimensions_parent, ndimensions, p, parse_string, pretty_input, pretty_output, random, random, set_variable, sqrt_variance, toString, update |
Noninformative
public Noninformative()
p
public double p(double[] x)
- Computes the density at the point
x.
Always returns 1.
effective_support
public double[] effective_support(double epsilon)
throws java.lang.Exception
- The support for a noninformative lambda or lambda message is unbounded.
- Specified by:
effective_support in interface Distribution- Overrides:
effective_support in class AbstractDistribution