Custom Distribution - Multivariate SkewNormal

ricardoV94 · December 20, 2023, 9:23pm

Actually the function _process_quantiles is not doing anything fancy so you should be able to implement a logp function for CustomDist without too much trouble.

github.com

scipy/scipy/blob/b3ba73a1526441824935e0c3d424415892bec84a/scipy/stats/_multivariate.py#L1185


      
                  if meanshape[1] != numcols:
                      raise ValueError("Arrays `mean` and `colcov` must have the "
                                       "same number of columns.")
              else:
                  mean = np.zeros((numrows, numcols))
          
              dims = (numrows, numcols)
          
              return dims, mean, rowcov, colcov
          
          def _process_quantiles(self, X, dims):
              """
              Adjust quantiles array so that last two axes labels the components of
              each data point.
              """
              X = np.asarray(X, dtype=float)
              if X.ndim == 2:
                  X = X[np.newaxis, :]
              if X.shape[-2:] != dims:
                  raise ValueError("The shape of array `X` is not compatible "
                                   "with the distribution parameters.")

You can get the MvNormal logp and Univariate Normal logcdf from pymc via pm.logp(pm.MvNormal.dist(mu, cov), x) and pm.logcdf(pm.Normal.dist(0, 1), x)

Topic		Replies	Views
Multivariate LogNormal distribution v5	18	1158	April 25, 2023
Implementing multivariate skew normal likelihood in PyMC v5	2	62	October 6, 2025
Examples of random() in custom distribution? Questions	19	4101	April 7, 2023
Build custom random method with reject sampling Questions	2	699	October 27, 2019
Call MvNormal.random() method inside model Questions	3	1159	August 29, 2018

Custom Distribution - Multivariate SkewNormal

Related topics