ABSTRACT
Chi square tests are typically used with nominal variables but they are also used with ordinal variables of few values and numerical variables that can be formed into subranges of values.There are two types of chi square test: the chi square goodness of fit test and the chi square test of independence. The chi square goodness of fit test is used to compare the distribution of cases among the values of some categorical variable with a theoretically expected distribution. For example, a gym may have 1,300 male members and 700 female members. The management of the gym would like to know if the 35 per cent of their members who are female is similar enough to the proportion of females in the wider population (assumed to be 50 per cent). The chi square goodness of fit test compares the observed distribution of the gym’s membership (1,300 males and 700 females) with a theoretically expected distribution (1,000 males and 1,000 females) to determine if the difference in these two distributions is down to chance or whether there is a significantly different gender distribution than expected.
