ABSTRACT
This chapter discusses the test whether the distribution of a categorical variable conforms to an expectation or deviates from that expectation. Information from the sample suggests that televised news stories about homicide are more likely to describe the homicide of a White victim than either a Black, Latino, or person of some other ethnic background, with such broadcasts accounting for 43% of televised news stories about homicide. There are many ways of quantifying association between categorical variables, but a treatment of even a small fraction of them would require a highly technical and lengthy discussion. The goodness of fit test is useful for determining whether several responses or objects are equally distributed across a number of categories or whether they distribute themselves consistent with some kind of expectation.
