91Ó°ÊÓ

The nominal level of measurement is used for variables that categorize data into distinct groups without any inherent order or ranking between them. This means you can label or name the categories, but you cannot say one category is 'higher' or 'better' than another. For instance, if we consider the variable 'gender', we can categorize individuals as 'male', 'female', or 'non-binary'. These categories are mutually exclusive and collectively exhaustive, meaning each individual fits into one category and there are no overlaps.

Other examples include:

• Types of fruits (e.g., apple, banana, cherry)
• Phone brand preferences (e.g., Samsung, Apple, Google)
• Marital status (e.g., single, married, divorced)

The key idea here is that while these categories identify different groups, they do not imply any sort of hierarchy or sequence.

The ordinal level of measurement deals with variables that can be categorized into distinct groups that do have a ranked order. However, the intervals between the ranks are not necessarily equal or meaningful. This means while you can determine if one category is ahead of another, the exact difference between the categories is not uniform or calculable.

A good example is a satisfaction survey with options like 'very satisfied', 'satisfied', 'neutral', 'unsatisfied', and 'very unsatisfied'. Here, you can clearly rank the responses from most to least satisfied.
Other examples include:

• Education levels (e.g., high school, bachelor's degree, master's degree, PhD)
• Socioeconomic status (e.g., lower class, middle class, upper class)
• Military ranks (e.g., private, corporal, sergeant, lieutenant)

It's important to note that while these categories have a specific order, the gaps between them are not quantifiable. For instance, the difference between 'very satisfied' and 'satisfied' may not be the same as the difference between 'neutral' and 'unsatisfied'.

The interval level of measurement involves variables that have not only order, but also equal intervals between values. This means that the differences between measurements are consistent across the scale. However, the interval level does not have a true zero point, which means we cannot make statements about how many times greater one value is compared to another.

A classic example of interval level measurement is temperature in degrees Celsius or Fahrenheit. For instance, the difference between 10°C and 20°C is the same as between 20°C and 30°C. Yet, neither 0°C nor 0°F is considered an absolute zero point, as temperatures can go below zero.
Other examples include:

• IQ scores
• Dates in the Gregorian calendar (e.g., the years 2000, 2010, 2020)
• Time of day in a 12-hour clock system (e.g., 1 PM, 2 PM, 3 PM)

The absence of an absolute zero is what differentiates interval scales from ratio scales, as we cannot say something like 20°C is 'twice as hot' as 10°C.

The ratio level of measurement is the most advanced level where variables have all the properties of interval measurement plus a true zero point. This allows for the comparison of both differences and ratios. A true zero point indicates the absence of the quantity being measured, making it possible to state how many times more or less one object or value is compared to another.

A quintessential example of ratio level measurement is weight. A weight of 0 kg means there is no weight, and it makes sense to say that 20 kg is twice as heavy as 10 kg.
Other examples include:

• Height (e.g., 150 cm, 160 cm, 170 cm)
• Income (e.g., \(0, \)50,000, $100,000)
• Distance (e.g., 0 meters, 5 meters, 10 meters)

Because of the true zero point, the ratio level allows the most versatility in statistical analysis, including geometric and logarithmic transformations, among others. This makes it especially useful for scientific and technical measurements.