Hello all, I feel like this may be a problem of simple misunderstanding… I have a model in which I sum a list of slope terms (slopes in the code below). If I have two slope terms and compute the predicted mean like mu = pm.Deterministic("mu", a[o] + slopes[0] + slopes[1]) then everything is fine…

`stack`ing and `sum`ing a list of random variables ruins sampling?

cluhmann May 13, 2022, 2:20pm 2

What shape is slopes? It’s not immediately clear to me why you are stacking before summing.

Topic		Replies	Views
Combining parameters into single tensor Questions	19	3538	October 30, 2017
Stacking priors problem Questions theano	1	673	December 1, 2021
Stacking distributions or changing distribution after assignment v5 modeling	6	800	September 12, 2022
Making a vector of variables from a list Questions	5	1258	December 28, 2017
How to vectorize indexing of variable for pm.math.sum? Questions	4	534	April 13, 2020