Skip to main content

interpret.InterpretResult

Unit-preserving posterior draws for predictions, contrasts, or slopes.

Usage

interpret.InterpretResult(
    *,
    ds,
    outcome,
    quantity,
    variable=None,
    estimator="structural",
    causal=False,
    interventional=False,
    identifiable=None
)

Internal storage is an xarray.Dataset with dims ("chain", "draw", "unit") exposed as dataset.

Parameters

ds: xr.Dataset

Labelled draws for the outcome variable.

outcome: str

Outcome variable name.

quantity: str

"prediction", "comparison", or "slope".

variable: str or None = None

Varied variable name, if any.

estimator: str = "structural"

Estimator backend label.

causal: bool = False

Whether the result supports a causal interpretation.

interventional: bool = False

Whether graph surgery / do() was used.

identifiable: bool or None = None
Backdoor identifiability when a treatment/outcome pair is defined.

Attributes

Name Description
causal Whether the result supports a causal interpretation.
dataset Labeled draws as an xarray.Dataset.
estimator Estimator backend that produced this result.
identifiable Backdoor identifiability of the treatment-outcome pair, if defined.
interventional Whether graph surgery / do() was used.
outcome The outcome variable this result targets.
quantity Query kind: prediction, comparison, or slope.
variable Varied variable name, if any.

causal

Whether the result supports a causal interpretation.

causal: bool

dataset

Labeled draws as an xarray.Dataset.

dataset: xr.Dataset

Variables use dims ("chain", "draw", "unit"). For a flat (n_samples,) numpy view, use draws() instead.

estimator

Estimator backend that produced this result.

estimator: str

identifiable

Backdoor identifiability of the treatment-outcome pair, if defined.

identifiable: bool | None

interventional

Whether graph surgery / do() was used.

interventional: bool

outcome

The outcome variable this result targets.

outcome: str

quantity

Query kind: prediction, comparison, or slope.

quantity: str

variable

Varied variable name, if any.

variable: str | None

Methods

Name Description
draws() Return flat posterior draws, defaulting to the outcome variable.
hdi() Return the highest-density interval, defaulting to the outcome.
mean() Return the posterior mean, defaulting to the outcome variable.
plot() Plot the marginal posterior of the outcome (mean over unit first).

draws()

Return flat posterior draws, defaulting to the outcome variable.

Usage

draws(var=None)

hdi()

Return the highest-density interval, defaulting to the outcome.

Usage

hdi(var=None, prob=DEFAULT_HDI_PROB)

mean()

Return the posterior mean, defaulting to the outcome variable.

Usage

mean(var=None)

plot()

Plot the marginal posterior of the outcome (mean over unit first).

Usage

plot(ax=None, *, var=None, bins=None)
Parameters
ax: matplotlib.axes.Axes or None = None

Axes to plot on. Creates a new figure when None.

var: str or None = None

Variable to plot. Defaults to the outcome.

bins: BinsLike or None = None
Passed through to matplotlib.axes.Axes.hist: a positive integer bin count, a binning strategy name such as "auto", or a sequence of bin edges.
Returns
matplotlib.figure.Figure
The figure containing the histogram.
Raises
ValueError
If bins is neither one of the accepted types nor, for an integer bin count, positive.