I’m using gp.Latent as a (top-level) prior in a hierarchical GLM to estimate parameter values in a mechanistic model of timeseries data (experimental instrument readings). The parameter estimates are well-defined and reasonable, but when I go to predict new parameters using gp.conditional the GP dra…

I tried running your collab, made a few tweaks and got: [image] Does this look right…? All I changed was: with latent_model: τ_new = gp.conditional('τ_new', Xnew=dim2_new) gp_draws = pm.sample_posterior_predictive(trace, vars=[τ_new])

Predictions from Latent GP in hierarchical model appear not conditioned on anything

Questions

BioGoertz July 1, 2020, 3:50pm 4

Apologies for the bump, but does anyone have suggestions here?

Topic		Replies	Views
Multivariate Gaussian Process Classification (GPC) and Prediction Questions	2	915	February 23, 2020
Using a Gaussian process at intermediate level in hierarchy Questions	3	899	May 17, 2020
`conditional` and Deep Gaussian Processes v5 gaussian_process	6	1001	April 17, 2023
How do you formulate a `Latent` GP that is equivalent to the `Marginal` implementation? Questions	5	503	May 26, 2021
Predicting on new data with gp.conditional Questions	7	1360	November 10, 2020

Predictions from Latent GP in hierarchical model appear not conditioned on anything

Related topics