Scales of Measurement Quiz

Study Notes

Nominal Data:
- Represents categories or names.
- No implied order to the categories, individuals are simply placed in the correct category.
- Examples include race, eye color, gender, marital status, religious affiliation, and blood group.
- Characteristic question: Is A different from B?

Has order among the response classifications (categories).
Intervals between the categories are not necessarily equal.
Examples include: strongly agree, agree, no opinion, disagree, strongly disagree, stages of disease, levels of pain, levels of satisfaction.
Characteristic question: Is A bigger than B?

Measurements are expressed in numbers, but the starting point is arbitrary and depends on the units of measurement.
The intervals between values are the same, for example, in the Fahrenheit temperature scale, the difference between 70 and 71 degrees is the same as the difference between 32 and 33 degrees.
The interval between any two intervals is dependent on their unit of measurement.
It is not a ratio scale, meaning 40 degrees Fahrenheit is not twice as hot as 20 degrees Fahrenheit.
Examples include temperature, psychiatric diagnostic instruments, SAT scores.
Characteristic question: By how many units do A differ from B?

Data values have meaningful ratios.
Has a true zero point and all properties of nominal, ordinal, and interval scales.
The ratio of any two measurements on the scale is physically meaningful.
Most data analysis techniques for ratio data also apply to interval data.
Examples include height, weight, length, and distance.
Characteristic question: How many times bigger than B is A?

Counting can be done for all types of variables (nominal, ordinal, interval, and ratio)

Established systems for continuous collection of health data.
Includes census, vital registration, hospital records, schools, armed forces, insurance, migration, and disease notification systems (DSN).

Special collections usually conducted when routine collections are inadequate.
Inadequacies result from incomplete, inaccurate, or non-existent data.
Aimed at specific time-limited studies or tasks.
Codified according to the goals and wishes of the investigator.
Examples include hospital-in-patient enquires, social surveys, demographic and health surveys (DHS), national reproductive health surveys (NARHS), and epidemiological surveys.
Data collection may cover the entire population or part of it.

Primary Data: Collected directly from respondents through surveys, meetings, focus group discussions (FGD), interviews, etc.
Secondary Data: Existing data collected for other purposes by organizations, government agencies, or research studies.

Discrete Variable:
- Has a set of values that are either finite or countably infinite.
- There are gaps between its possible values.
- Often take integers (whole numbers), but some can take non-integer values.
- Examples include the number of children, pregnancies, and episodes of diarrhea.
Continuous Variables
- A measurement on a continuous scale.
- Has a set of possible values including all values in an interval of the real line.
- Examples include weight, height, blood pressure, age, and BMI.

The process of systematically assigning numbers to objects and their properties to facilitate using mathematics to study and describe objects and their relationships.
Measurement is not limited to physical qualities like height and weight.
Tests to measure abstract constructs like intelligence or scholastic aptitude are forms of measurement.

Scales of Measurement refer to ways in which variables/numbers are defined and categorized.
Each scale of measurement has certain properties that determine the appropriateness of certain statistical analyses.
The four scales of measurement are nominal, ordinal, interval, and ratio.

In education and psychology, measurement is often used to assess abstract constructs like intelligence, aptitude, or personality traits using various tools like standardized tests, scales, and questionnaires.
Measurement helps to quantify subjective experiences and characteristics, allowing researchers to draw conclusions and compare individuals or groups based on measured scores.

Crucial for researchers, data analysts, and professionals in various fields to choose the appropriate statistical methods and analyses for their data, ensuring accurate interpretations and reliable conclusions.
By correctly identifying the level of measurement of a variable, researchers can appropriately select statistical tests and measures of association, ensuring the validity of their findings.
Understanding scales of measurement is essential for making informed decisions about data analysis, interpretation, and reporting, leading to more reliable and meaningful insights.