Variable measurement scale

Variable measurement scale in statistics is a way of classifying the type of information that a variable can record. There are four main scales of measurement: nominal, ordinal, interval, and ratio. Each scale has different properties and implications for data analysis.

• Nominal scale: The data can only be categorized by labels or names, but there is no order or ranking between the categories. For example, gender, ethnicity, and car brands are nominal variables. Also data type like true vs false, pass vs fail fall come under category.

• Ordinal scale: The data can be categorized and ranked by order, but the intervals between the ranks are not equal or known. For example, language ability, school rankings are ordinal variables. Also, Likert-type questions fall under this category e.g. ranking customer satisfaction level on a 1 to 5 scale, where 1 = very dissatisfied, 2 = dissatisfied, 3 = neutral, 4 = satisfied, and 5 = very satisfied. Ordinal scale data involves a stronger form of dataset than nominal scale type attribute data.

• Interval scale: The data can be categorized, ranked, and have equal intervals between adjacent values, but there is no true zero point. For example, temperature, test scores, and personality inventories are interval variables.

• Ratio scale: The data can be categorized, ranked, have equal intervals, and have a true zero point that indicates the absence of the variable. For example, height, weight, and income are ratio variables.