Chi squared (or Χ²) is the name of probability distrubution which is the sum of a number of Normal distribution random variables. It is typically encountered in contingency tables, as a measure of whether inbalances in the frequencies represent a real effect or just randomness. This is then used as a metric in some machine learnng techniques, notable decison tree construction, to avoid over learning.
Used on Chap. 21: page 522