Hi all, I’m using the JAX support in PyMC and I have a question. I believe that by default, PyMC transforms positive random variables to the full real line by using the logarithm. I’d be interested whether it’s possible to use a different transformation instead, like maybe a square root (though tha…

+1 that a none bijective transformation should not be used. In general, you can supply custom transformation by supplying it to transform kwarg: pm.Uniform('a', ..., transform=...), the transformation PyMC currently provides are in pymc/transforms.py at main · pymc-devs/pymc · GitHub

Custom transformations for positive random variables?

Questions version agnostic

ricardoV94 August 28, 2022, 1:50pm 2

Other transformations can be done, but why a square root transform?

1 Like

Topic		Replies	Views
Jacobian adjustment Questions	1	1521	August 13, 2018
Circular transformation has a zero-valued Jacobian Questions	6	941	September 12, 2018
Bounded variable logp Questions	6	902	August 15, 2018
Bounded variable transformation when not using HMC? version agnostic	8	628	February 14, 2023
ADVI transofrmations Questions	1	307	February 9, 2021

Custom transformations for positive random variables?

Related topics