Plot Leave-One-Out (LOO) probability integral transformation (PIT) predictive checks.
InferenceData
arviz.InferenceData object.
array, DataArray or str
Observed data. If str, idata must be present and contain the observed data group
array, DataArray or str
Posterior predictive samples for y. It must have the same shape as y plus an extra dimension at the end of size n_samples (chains and draws stacked). If str or None, idata must contain the posterior predictive group. If None, y_hat is taken equal to y, thus, y must be str too.
array or DataArray
Smoothed log_weights. It must have the same shape as y_hat
Plot the difference between the LOO-PIT Empirical Cumulative Distribution Function (ECDF) and the uniform CDF instead of LOO-PIT kde. In this case, instead of overlaying uniform distributions, the beta hdi_prob around the theoretical uniform CDF is shown. This approximation only holds for large S and ECDF values not very close to 0 nor 1. For more information, see Vehtari et al. (2021), Appendix G.
Use matplotlib.axes.Axes.fill_between() to mark the area inside the credible interval. Otherwise, plot the border lines.
int, optional
Number of datasets to simulate and overlay from the uniform distribution.
Compute expected hdi values instead of overlaying the sampled uniform distributions.
float, optional
Probability for the highest density interval. Works with use_hdi=True or ecdf=True.
float, float), optional
If None, size is (8 + numvars, 8 + numvars)
int, optional
Text size for labels. If None it will be autoscaled based on figsize.
Class providing the method make_pp_label to generate the labels in the plot titles. Read the Label guide for more details and usage examples.
str or array_like, optional
Color of the LOO-PIT estimated pdf plot. If plot_unif_kwargs has no “color” key, a slightly lighter color than this argument will be used for the uniform kde lines. This will ensure that LOO-PIT kde and uniform kde have different default colors.
Show the legend of the figure.
axes, optional
Matplotlib axes or bokeh figures.
dict, optional
Additional keywords passed to matplotlib.axes.Axes.plot() for LOO-PIT line (kde or ECDF)
dict, optional
Additional keywords passed to matplotlib.axes.Axes.plot() for overlaid uniform distributions or for beta credible interval lines if ecdf=True
dict, optional
Additional keywords passed to matplotlib.axes.Axes.axhspan()
dict, optional
Additional kwargs passed to matplotlib.axes.Axes.fill_between()
str, optional
Select plotting backend {“matplotlib”,”bokeh”}. Default “matplotlib”.
These are kwargs specific to the backend being used, passed to matplotlib.pyplot.subplots() or bokeh.plotting.figure(). For additional documentation check the plotting method of the backend.
Call backend show function.
matplotlib Axes or bokeh_figures
See also
plot_bpv
Plot Bayesian p-value for observed data and Posterior/Prior predictive.
loo_pit
Compute leave one out (PSIS-LOO) probability integral transform (PIT) values.
References
Gabry et al. (2017) see https://arxiv.org/abs/1709.01449
Gelman et al. BDA (2014) Section 6.3
Examples
Plot LOO-PIT predictive checks overlaying the KDE of the LOO-PIT values to several realizations of uniform variable sampling with the same number of observations.
>>> import arviz as az
>>> idata = az.load_arviz_data("radon")
>>> az.plot_loo_pit(idata=idata, y="y")
Fill the area containing the 94% highest density interval of the difference between uniform variables empirical CDF and the real uniform CDF. A LOO-PIT ECDF clearly outside of these theoretical boundaries indicates that the observations and the posterior predictive samples do not follow the same distribution.
>>> az.plot_loo_pit(idata=idata, y="y", ecdf=True)
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4