pymc.Bernoulli#

class pymc.Bernoulli(name, *args, **kwargs)[source]#

Bernoulli log-likelihood

The Bernoulli distribution describes the probability of successes (x=1) and failures (x=0). The pmf of this distribution is

\[f(x \mid p) = p^{x} (1-p)^{1-x}\]

(Source code, png, hires.png, pdf)

../../../_images/pymc-Bernoulli-1.png

Support

\(x \in \{0, 1\}\)

Mean

\(p\)

Variance

\(p (1 - p)\)

The bernoulli distribution can be parametrized either in terms of p or logit_p. The link between the parametrizations is given by

\[logit(p) = ln(\frac{p}{1-p})\]
Parameters
ptensor_like of float

Probability of success (0 < p < 1).

logit_ptensor_like of float

Alternative log odds for the probability of success.

Methods

Bernoulli.__init__(*args, **kwargs)

Bernoulli.dist([p, logit_p])

Creates a tensor variable corresponding to the cls distribution.

Bernoulli.logcdf(p)

Compute the log of the cumulative distribution function for Bernoulli distribution at the specified value.

Bernoulli.logp(p)

Calculate log-probability of Bernoulli distribution at specified value.

Bernoulli.moment(size, p)

Attributes

rv_class

rv_op