I am trying to figure out whether it is possible to have a distribution present when an indicator variable is =1, and not present when it is = 0. e.g. in the following example, I want lp to only be Gaussian when v_i == 1, and to just be 0 otherwise. (of course for this simple example I could just …

You can also stack the different RV together, and use the observed v_i to index them: v = np.random.randint(2, size=100) with pm.Model() as m: RV1 = pm.Normal('rv1', 0, 1) RV2 = pm.Flat('rv2') # Flat distribution returns 0 logp rvall_logp = tt.stack([RV1.logpt, RV2.logpt]) observed …

Indicator from independent variable sets distribution or zero

Questions

jrmxn July 30, 2018, 10:52am 3

OK - sounds good! Thanks.

Topic		Replies	Views
How to model a multistep logic Questions	0	340	March 12, 2020
Condition Categorical Variable on Bernoulli Parents Questions	16	2340	May 14, 2019
Observed variable using custom function Questions	1	669	December 14, 2017
Best way to model a observed variable that is a mixture of two distributions Questions	2	878	November 19, 2018
RV-Dependent Observations from Irregularly-Shaped Dataset Questions	8	987	July 26, 2017

Indicator from independent variable sets distribution or zero

Related topics