criterium.random.ziggurat — org.hugoduncan/criterium.arg-gen 0.5.245-ALPHA

Ziggurat algorithm for generating normal random variates.

See: An improved Ziggurat method to generate normal random samples, Doornik, 2005

make-normal-rng clj

(make-normal-rng)

(make-normal-rng uniform-rng)

(make-normal-rng uniform-rng c r v)

Create a NormalRng instance for generating standard normal variates. Returns a mutable RNG that generates doubles from N(0,1) via next-gaussian!.

Arities:

• () - Uses default WELL RNG with standard ziggurat parameters
• (uniform-rng) - Uses provided WellRng1024a with standard parameters
• (uniform-rng c r v) - Uses provided RNG with custom ziggurat parameters

Standard parameters: c=128 blocks, r=3.442619855899, v=9.91256303526217e-3

See: An improved Ziggurat method to generate normal random samples, Doornik, 2005

next-gaussian! clj

(next-gaussian! rng)

Generate the next random gaussian in N(0,1), mutating the RNG state. Returns a double.

sqr clj macro

(sqr x)

zignor-c clj

Number of blocks.

zignor-init clj

(zignor-init c r v)

Initialise tables.

zignor-r clj

Start of the right tail: (R * phi(R) + Pr(X>=R)) * sqrt(2pi)

zignor-v clj