![Home](http://my.ilstu.edu/~oakman/dataanalysis/_derived/home_cmp_copy-of-blank010_hbtn.gif)
![Up](http://my.ilstu.edu/~oakman/dataanalysis/_derived/up_cmp_copy-of-blank010_hbtn.gif)
![One Group](http://my.ilstu.edu/~oakman/dataanalysis/_derived/1_group1.htm_cmp_copy-of-blank010_hbtn_p.gif)
![Two Groups](http://my.ilstu.edu/~oakman/dataanalysis/_derived/2_groups1.htm_cmp_copy-of-blank010_hbtn.gif)
![Three or More Groups](http://my.ilstu.edu/~oakman/dataanalysis/_derived/3_groups.htm_cmp_copy-of-blank010_hbtn.gif)
With nominal measures, expected values are determined by multiplying the total number of observations in the sample by the proportion of a particular outcome, or np. The expected value for all other outcomes is the total number of outcomes times one minus the proportion of that outcome, or n(1-p). The statistical method used for one group depends on these expected values.
![np and n(1-p) >5](http://my.ilstu.edu/~oakman/dataanalysis/_derived/np_and_nq5.htm_cmp_copy-of-blank010_hbtn.gif)
![np and n(1-p) <5](http://my.ilstu.edu/~oakman/dataanalysis/_derived/np_and_nq51.htm_cmp_copy-of-blank010_hbtn.gif)