Nominal and Ordinal Data
Data collection becomes major characteristic of qualitative data, that there is no decimal score. For instance, gender, blood type, residence, or work types data.
As examples, gender data consists of male and female, the content is how many males and females. It requires calculation, for example, obtained 15 males and 25 females. Here, there is no way that the calculation result is 15,4 males and 25,1 females, because male and female do not have decimal.
This becomes the basic difference with quantitative data which has decimal using measurement.
To process non numeric or non metric or qualitative data, the data should be converted into number, this is called as categorization process.
The first qualitative data is Nominal Data, such as gender variable. On the gender data, it is conducted by giving codes/categories for gender types, for example code "1" stands for male and "2" stands for female.
Another example is residence, by giving code, such as code "1" for Washington, code "2" for New York, code "3" for LA, and code "4" for Detroit.
Data Ordinal is the second qualitative data. Unlike nominal one, this data has order and sequence. Consumers attitude data is an example. The content logically is constructed as follows :
Strongly Agree code 1
Agree code 2
Neutral code 3
Disagree code 4
Strongly Disagree code 5
This shows the basic difference with nominal data which is unnecessarily ordered. On nominal data, the male one with code "1" and the female one with code "2" is possibly reversed into male with code "2" and female with code "1", therefore ordinal data is not commonly haphazard ordered.
