pymc.HalfFlat

class pymc.HalfFlat(name, *args, rng=None, dims=None, initval=None, observed=None, total_size=None, transform=UNSET, default_transform=UNSET, **kwargs)

Improper flat prior over the positive reals.

This is an unnormalized distribution and should be used only as a vague, uninformative prior. It is not a valid probability distribution and cannot be used for posterior predictive sampling.

The pdf of this distribution is

\[\begin{split}f(x) \propto \begin{cases} 1 & \text{if } x > 0 \\ 0 & \text{otherwise} \end{cases}\end{split}\]

Support	\(x \in [0, \infty)\)
Mean	undefined
Variance	undefined

Examples

with pm.Model():
    x = pm.HalfFlat("x")

Methods

HalfFlat.dist(**kwargs)

Create a tensor variable corresponding to the cls distribution.