arviz.effective_sample_size¶

arviz.
effective_sample_size
(data, *, var_names=None, method='bulk', relative=False, prob=None)[source]¶ Calculate estimate of the effective sample size.
Function deprecated. Use arviz.ess.
 Parameters
 dataobj
Any object that can be converted to an az.InferenceData object. Refer to documentation of az.convert_to_dataset for details. For ndarray: shape = (chain, draw). For ndimensional ndarray transform first to dataset with az.convert_to_dataset.
 var_nameslist
Names of variables to include in the effective_sample_size_mean report
 methodstr
Select ess method. Valid methods are  “bulk”  “tail” # prob, optional  “quantile” # prob  “mean” (old ess)  “sd”  “median”  “mad” (mean absolute deviance)  “z_scale”  “folded”  “identity”
 relativebool
Return relative ess ress = ess / N
 probfloat, optional
probability value for “tail” and “quantile” ess functions.
 Returns
 xarray.Dataset
Return the effective sample size for mean, \(\hat{N}_{eff}\)
Notes
The basic ess diagnostic is computed by:
\[\hat{N}_{eff} = \frac{MN}{\hat{\tau}}\]\[\hat{\tau} = 1 + 2 \sum_{t'=0}^K \hat{P}_t'\]where \(\hat{\rho}_t\) is the estimated _autocorrelation at lag t, and T is the first odd positive integer for which the sum \(\hat{\rho}_{T+1} + \hat{\rho}_{T+1}\) is negative.
The current implementation is similar to Stan, which uses Geyer’s initial monotone sequence criterion (Geyer, 1992; Geyer, 2011).
References
Vehtari et al. (2019) see https://arxiv.org/abs/1903.08008 https://mcstan.org/docs/2_18/referencemanual/effectivesamplesizesection.html Section 15.4.2 Gelman et al. BDA (2014) Formula 11.8