estimator.prob.conditional_chi_squared

estimator.prob.conditional_chi_squared#

estimator.prob.conditional_chi_squared(d1, d2, lt, l2)[source]#

Probability that a gaussian sample (var=1) of dim d1+d2 has length at most lt knowing that the d2 first coordinates have length at most l2

Parameters:
  • d1 – Dimension of non length-bounded coordinates

  • d2 – Dimension of length-bounded coordinates

  • lt – Length threshold (maximum length of whole vector)

  • l2 – Length threshold for the first d2 coordinates.

EXAMPLE::
>>> from estimator import prob
>>> prob.conditional_chi_squared(100, 5, 105, 1)
0.6358492948586715
>>> prob.conditional_chi_squared(100, 5, 105, 5)
0.5764336909205551
>>> prob.conditional_chi_squared(100, 5, 105, 10)
0.5351747076352109
>>> prob.conditional_chi_squared(100, 5, 50, 10)
1.1707597206287592e-06
>>> prob.conditional_chi_squared(100, 5, 50, .7)
5.4021875103989546e-06