The chi-square goodness-of-fit test is almost always:

1. Evidence against the null shows up as a large test statistic. 2. A large statistic sits far out in one particular tail. 3. The goodness-of-fit test is almost always right-tailed. 4. A small statistic instead means observed and expected values agree closely. _Source: OpenStax Introductory Statistics 2e (CC BY 4.0), Ch 11 'The Chi-Square Distribution', sections 11.1-11.5_