This tutorial provides definitions and examples for the 3 SPSS measures, including nominal, ordinal, and scale.
Definitions for Nominal, Ordinal, and Scale
Variables at the nominal level are categorical and have no inherent order or numerical meaning. Examples include gender (e.g., male or female), ethnicity (e.g., Asian, African American, Caucasian), or marital status (e.g., married, single, divorced). In SPSS, you can code nominal variables using numerical values or assign labels to each category.
Variables at the ordinal level have categories with a meaningful order or ranking but do not necessarily have equal intervals between them. Examples include Likert scale items (e.g., strongly disagree, disagree, neutral, agree, strongly agree) or educational attainment (e.g., high school, bachelor’s degree, master’s degree, PhD). In SPSS, you can assign numerical values to ordinal categories to represent their relative order.
Variables at the scale level have numerical values that have equal intervals between them, and they have a meaningful zero point. Scale variables are quantitative and allow for arithmetic operations such as addition and subtraction. Examples include age (e.g., 18, 19, 22, 89…) and income (e.g.,10,000, 30,000, …..). In SPSS, you can treat scale variables as continuous measurements and perform various statistical analyses on them.
Of note, we can calculate means for scale data. In contrast, you can not calculate means for nominal or ordinal measures.
Difference between Nominal and Ordinal Data
The similarity between nominal and ordinal data is that they are categorical variables, and thus it does not make sense to calculate means for either of them.
For instance, you can code male =1 and female =0, but you still should not calculate the mean for the gender variable. Similarly, you will not calculate means for the ordinal variables either.
The key difference between nominal and ordinal data is that nominal data is not ordered, while ordinal data is ordered. For instance, jobs with different levels of income can be ordered as a way to represent the magnitude difference.
Difference between Scale, Interval, and Ratio
Scale in SPSS can be used for either interval or ratio data. Thus, SPSS does not distinguish between interval and ratio data. The following explain the difference between interval data and ratio data.
Interval data is a type of quantitative data that has a numerical scale with equal intervals between values. In interval data, the numerical values represent the magnitude of the variable, and the intervals between values are consistent and measurable.
An essential characteristic of interval data is that it does not have a meaningful zero point. Zero in interval data does not indicate the absence of the measured attribute but serves as a reference point. For example, temperature measured in degrees Celsius or Fahrenheit is considered interval data. In this case, zero degrees does not mean the complete absence of temperature but serves as an arbitrary reference point.
With interval data, you can perform various mathematical operations, such as addition and subtraction. Additionally, you can calculate measures like means, standard deviations, and perform statistical tests like t-tests or analysis of variance (ANOVA).
It’s important to note that interval data is different from ratio data. Ratio data, in addition to having equal intervals, also possesses a meaningful zero point that represents the absence of the measured attribute. Common examples of ratio data include weight, height, and income.
Ratio data is a type of quantitative data that possesses all the properties of interval data and, additionally, has a meaningful zero point. In ratio data, the numerical values not only represent the magnitude of the variable but also allow for meaningful ratios and comparisons between values.
The key characteristic of ratio data is that zero represents the absence or complete lack of the measured attribute. Ratios between values are meaningful and can be calculated. For example, if you have variables such as weight, height, time, or income measured in a specific unit, you can perform arithmetic operations such as addition, subtraction, multiplication, and division.
With ratio data, you can calculate various descriptive statistics, such as means, medians, ranges, standard deviations, and percentages. Additionally, you can perform a wide range of statistical analyses, including correlation analysis, regression analysis, and inferential tests like t-tests and ANOVA.
It’s worth noting that ratio data is considered the highest level of measurement, providing the most precise and informative data for analysis.
The following shows the reference that you can read further.