Research Analysis

Variables and Behavioral Studies

Quantitative experiments or research studies are often carried out to search for cause-and-effect relationships or some other form of measurable data. In other words, scientists and researchers design their experiments so that changes to one item cause something else to vary in a predictable way. These changing quantities are called variables. A variable is any factor, trait, or condition that can exist in differing amounts or types. For example, height, gender, hair color, social status, personality type, educational level, and reaction time are all variables. We can quantify these variables in different ways. For example, you could quantify hair color by creating different categories and counting the number of people who have different colors of hair (e.g., red, brown, blonde). On the other hand, height is a continuous variable that could be quantified by measuring how tall a person is (ranging from the height of an infant to the height of the tallest person on Earth).

There are different groups or types of variables. After examining the different types of variables, let's focus on how to measure these variables.

The first level of measurement is nominal level of measurement.  In this level of measurement, the numbers in the variable are used only to classify the data.  In this level of measurement, words, letters, and alpha-numeric symbols can be used.  Suppose there are data about people belonging to three different gender categories. In this case, the person belonging to the female gender could be classified as F, the person belonging to the male gender could be classified as M, and transgendered classified as T.  This type of assigning classification is nominal level of measurement.

The second level of measurement is the ordinal level of measurement.  This level of measurement depicts some ordered relationship among the variable's observations.  Suppose a student scores the highest grade of 100 in the class.  In this case, he would be assigned the first rank.  Then, another classmate scores the second highest grade of an 92; she would be assigned the second rank.  A third student scores a 81 and he would be assigned the third rank, and so on.   The ordinal level of measurement indicates an ordering of the measurements.

The third level of measurement is the interval level of measurement.  The interval level of measurement not only classifies and orders the measurements, but it also specifies that the distances between each interval on the scale are equivalent along the scale from low interval to high interval.  For example, an interval level of measurement could be the measurement of anxiety in a student between the score of 10 and 11, this interval is the same as that of a student who scores between 40 and 41.   A popular example of this level of measurement is temperature in centigrade, where, for example, the distance between 940C and 960C is the same as the distance between 1000C and 1020C.

The fourth level of measurement is the ratio level of measurement.  In this level of measurement, the observations, in addition to having equal intervals, can have a value of zero as well.  The zero in the scale makes this type of measurement unlike the other types of measurement, although the properties are similar to that of the interval level of measurement.  In the ratio level of measurement, the divisions between the points on the scale have an equivalent distance between them.

We use a scale of measurement to measure the variables in a research study. There are generally different categories that we can consider when grouping the variables. We use the scale of measurement as a way to organize the data that is collected during the study. For example, an ordinal scale is one type of scale of measurement that can be used in research. An ordinal scale uses a rank order. Suppose you want to measure a worker's reliability. You can measure it on an ordinal scale as very reliable or not reliable. You might also choose a different type of scale of measurement, called a ratio scale, which uses an interval scale that begins with a zero and look at the number of days the worker is late in a year.

Understanding Operational Definition

Another concept that is related to variables is that of operational definitions. An operational definition provides a very specific statement about how a variable will be measured. For example, when thinking about a rat's ability to navigate a maze, you can use the number of mistakes the rat makes while navigating the maze as a way to assess maze learning. The number of mistakes the rat makes can serve as the operational definition of maze learning.

Operational definitions are provided in research studies not only for understanding what was measured, but also for replicating the study in the future.

Note: Other researchers often replicate research for various reasons. The process is similar to following a recipe. For example, if you are trying to bake the same cake that a friend made earlier, you need to use the same ingredients in the same proportions. The operational definition is a recipe for measurement in a research study.

Experiments that manipulate variables are commonly used study designs for a research study. You can also choose descriptive and correlational study designs for a quantitative research study. The goal of a descriptive study is to describe data and the characteristics of the population being studied. Correlational studies enable you to determine if there is a significant relationship between variables. This type of design allows you to understand the variables that are connected to each other without manipulating any of the variables.

Let's first illustrate a descriptive study. For example, based on the media piece above, researchers can describe what they noticed and speculate about the behaviors; however, researchers cannot conclude that being an adult learner leads to stress. Why not? Many other variables could have led to the apparent differences, and you have not scientifically tested these factors. What if a younger student had to take a night class, and you notice that he or she is less talkative and appeared stressed? In that case, the apparent difference in behavior might be a function of the time of the day and not the age of the student.