In multivariate case this won’t work, currently the missing value feature in pymc3 only handles 1d case. You can have a look at some related discussion here: OOS predictions with missing input values
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Dealing with partially observed multivariate Normal values | 3 | 1730 | January 7, 2019 | |
| Partial Missing Multivariate Observation and What to Do With Them by Junpeng Lao | 4 | 1831 | October 31, 2020 | |
| Handling missing values in predictor when outcome is a Multivariate Normal distribution | 7 | 274 | October 25, 2024 | |
| Marginalizing over missing categories | 1 | 761 | June 17, 2020 | |
| Dealing with missing data and custom distribution | 13 | 2337 | March 14, 2021 |