ppi_noise_threshold: Estimate the 95th Percentile of a Projection Pursuit Index...

In spinebil: Investigating New Projection Pursuit Index Functions

Estimate the 95th Percentile of a Projection Pursuit Index Under Noise

Description

This function estimates the 95th percentile of a projection pursuit index under synthetic noise data.

Usage

ppi_noise_threshold(
  index_fun,
  n_sim = 100,
  n_obs = 500,
  noise_type = "gaussian",
  noise_level = 0.01,
  seed = NULL
)

Arguments

index_fun	A function that takes either a 2-column matrix or two numeric vectors and returns a scalar index.
n_sim	Integer. Number of index evaluations to simulate. Default is 100.
n_obs	Integer. Number of observations per noise sample. Default is 500.
noise_type	Character. Type of noise to use (e.g., "gaussian", "t_distributed", etc.). Default is "gaussian".
noise_level	Numeric. Controls the scale/spread of the generated noise. Default is 0.01.
seed	Optional integer. Random seed for reproducibility.

Value

A single numeric value: the estimated 95th percentile of the index under noise.

Examples

ppi_noise_threshold(
  index_fun = scag_index("stringy"),
  noise_type = "cauchy",
  noise_level = 0.1,
  n_sim = 10,
  n_obs = 100
)

spinebil documentation built on Nov. 5, 2025, 7:35 p.m.