You are viewing documentation for the old version 2.20 of Analyse-it. If you are using version 3.00 or later we recommend you go to the latest documentation.

About Nominal & Ordinal scale

Categorical data, where the observations of a variable are classified into one of a number of mutually-exclusive groups, is classified into two measurement scales for analysis:

  • Nominal scale where the groups do not have a natural ordering. For example Male & Female.
  • Ordinal scale where the groups do have a natural ordering. For example Ratings of Low, Medium and High, where Low < Medium < High.

By default Analyse-it assumes all variables are measured on a continuous scale, so for nominal and ordinal variables the measurement scale must be set (see Setting measurement scale for a variable).

Observations for nominal and ordinal scale data can be entered as group names, e.g. Male & Female, or as numeric codes, e.g. 1 & 2. Numeric codes are often used for brevity and quick data entry, but their meaning can be difficult to interpret and remember. To aid comprehension codes can be mapped to group names (see Mapping group names to codes).