bf.dist.truncated_normal: Truncated Normal Distribution

In BayesForge: Bayesian Inference using 'numpyro' and 'XLA'

Truncated Normal Distribution

Description

A truncated normal distribution is derived from a normal (Gaussian) random variable by restricting (truncating) its domain to an interval

[a, b]

(which could be one-sided, e.g., (a) only or (b) only). It is defined by its location ('loc'), scale ('scale'), lower bound

a

('low'), and upper bound

b

('high'). In effect: if

X \sim \mathcal N(\mu, \sigma^2)

, then the truncated version

Y = X | (a \le X \le b)

has the same "shape" but only supports values in

[a,b]

. This is used when you know that values outside a range are impossible or not observed (e.g., measurement limits, natural bounds).

Usage

bf.dist.truncated_normal(
  loc = 0,
  scale = 1,
  low = py_none(),
  high = py_none(),
  validate_args = py_none(),
  name = "x",
  obs = py_none(),
  mask = py_none(),
  sample = FALSE,
  seed = py_none(),
  shape = c(),
  event = 0,
  create_obj = FALSE,
  to_jax = TRUE
)

Arguments

loc	The location parameter of the normal distribution.
scale	The scale parameter of the normal distribution.
low	(float, jnp.ndarray, optional): The lower truncation point. If 'None', the distribution is only truncated on the right. Defaults to 'None'.
high	(float, jnp.ndarray, optional): The upper truncation point. If 'None', the distribution is only truncated on the left. Defaults to 'None'.
validate_args	Logical: Whether to validate parameter values. Defaults to 'reticulate::py_none()'.
name	A character string representing the name of the random variable within a model. This is used to uniquely identify the variable. Defaults to 'x'.
obs	A numeric vector or array of observed values. If provided, the random variable is conditioned on these values. If 'NULL', the variable is treated as a latent (unobserved) variable. Defaults to 'NULL'.
mask	An optional boolean array to mask observations.
sample	A logical value that controls the function's behavior. If 'TRUE', the function will directly draw samples from the distribution. If 'FALSE', it will create a random variable within a model. Defaults to 'FALSE'.
seed	An integer used to set the random seed for reproducibility when 'sample = TRUE'. This argument has no effect when 'sample = FALSE', as randomness is handled by the model's inference engine. Defaults to 0.
shape	A numeric vector (e.g., 'c(10)') used to shape the distribution. When 'sample=False' (model building), this is used with '.expand(shape)' to set the distribution's batch shape. When 'sample=True' (direct sampling), this is used as 'sample_shape' to draw a raw JAX array of the given shape.
event	The number of batch dimensions to reinterpret as event dimensions (used in model building).
create_obj	Logical; If 'TRUE', returns the raw BI distribution object instead of creating a sample site.
to_jax	Boolean. Indicates whether to return a JAX array or not.

Value

- When sample=FALSE, a BI Truncated Normal distribution object (for model building).

- When sample=TRUE, a JAX array of samples drawn from the Truncated Normal distribution (for direct sampling).

- When create_obj=TRUE, the raw BI distribution object (for advanced use cases).

Examples

library(BayesForge)
m=importBF(platform='cpu')
bf.dist.truncated_normal(loc = 0, scale = 2, low = 0, high = 1.5, sample = TRUE)

BayesForge documentation built on June 9, 2026, 1:09 a.m.