Search All of the Math Forum:
Views expressed in these public forums are not endorsed by
Drexel University or The Math Forum.



Re: nominal scale  comparison of populations
Posted:
Dec 23, 2012 6:47 PM


<czytaczgrup@gmail.com> wrote in message news:49a8c8322239487d85ddc93bb8ad1932@googlegroups.com... Hi,
Using a short questionnaire I have interviewed two populations. For majority of questions the answers are of the nominal type only (there are more than two possible answers which are self excluding and complete). Now, I would like to check if these populations are/are not the same with respect to the frequencies given to answers. Therefore, the every possible answer was coded as a distinct integer number. This gives me a probability distribution. Can I use statistical tests to compare these distributions? If yes  would be the outcome of a test robust to the way in which the numbers are adjusted?
 I really have no business commenting here, I am merely an introductory level tutor. but your question might be elementary  you have categorical data such as (to take an example using automobiles) color, style, etc. For data encoding purposes you may designate blue = 1, red =2, white = 3, etc. But to treat this data as a single variable with ordinal or cardinal rank is absurd. In what sense would white be 50% more than red and three times blue, or even white > red > blue ? OK, you didn't mention rank, so presumably you are aware of that.
Next, you can deal with proportions  are there differences in colors among different body stayles? I would attack such questions using chisquare methods or perhaps ANOVA. Look up "test of homogeneity" in a standard stats text, for example. Does that help?



