chi2pdf

Builtin index · Statistics & ML

result = chi2pdf(x, k)

Input: x, k · Output: result

What it is

Chi-square probability density at x (a number or vector, elementwise) with k degrees of freedom (a positive number), computed in log space so it survives modest k without overflowing.

Overloads

One call shape — this function is not overloaded.

Code	Input	Output	Description
`result = chi2pdf(x, k)`	`x` number or vectornot documented yet `k` number or vectornot documented yet	`result` number or vector	Returns a number or vector the same shape as `x`.

Examples

From the documentation, and run by the build -- the output and the figure below are what the engine actually produced. Simplest first.

seed(42)                             # reseed the shared stream

u = rand(3, seed = 1)                # an explicit seed still wins

print("rand draws: {round(u, 3)}")
print("chi2pdf(2, 3):  {round(chi2pdf(2, 3), 4)}")
print("normpdf(0):     {round(normpdf(0), 4)}")

walk = random_walk(20, drift = 0.1, volatility = 1.0, seed = 3)
print("random walk, last value: {round(walk[19], 3)}")

output

rand draws: [0.746, 0.971, 0.444]
chi2pdf(2, 3):  0.2076
normpdf(0):     0.3989
random walk, last value: -3.552

from statistics-ml

How it works

chi2pdf(x, k) — the chi-square density with k degrees of freedom, computed in log-space via ln_gamma (the naive x^(k/2-1)*exp(-x/2)/(2^(k/2)*Gamma(k/2)) overflows/ underflows for even modest k) then exponentiated. Broadcasts over a vector x like any elemental-math builtin.

From the note above this builtin in the interpreter, where the reasoning was written down as it was built.