zhusuan.diagnostics¶
-
effective_sample_size
(samples, burn_in=100)¶ Compute the effective sample size of a chain of vector samples, using the algorithm in Stan. Users should flatten their samples as vectors if not so.
Parameters: - samples – A 2-D numpy array of shape
(M, D)
, whereM
is the number of samples, andD
is the number of dimensions of each sample. - burn_in – The number of discarded samples.
Returns: A 1-D numpy array. The effective sample size.
- samples – A 2-D numpy array of shape
-
effective_sample_size_1d
(samples)¶ Compute the effective sample size of a chain of scalar samples.
Parameters: samples – A 1-D numpy array. The chain of samples. Returns: A float. The effective sample size.