From the course: Academic Research Foundations: Quantitative

Independent and dependent variables - SPSS Statistics Tutorial

From the course: Academic Research Foundations: Quantitative

Start my 1-month free trial

Independent and dependent variables

“

- [Instructor] You probably remember a science teacher talking about independent and dependent variables in middle and high school. If you're like me, you've probably gone to the Internet more than once to try to remember which is which. It can be tough to see the difference in theory rather than in practice. So let's start with independent and dependent variable definitions by thinking about the concept of variables themselves. In research, a variable is a data set or a measurement of an item that consists of different values. In quantitative research, you can think about this in terms of numbers. A researcher could use age as a variable or height or a test score. Variables aren't limited to number values. Your data set could be colors or elected officials or countries. So a variable is not about a specific value, but instead about a group, which will have multiple values within its constraints. If your variable is color, you could have red and blue and green, but you could not have spaceship. In the same way, if your variable is age, you could have 18 and 44 and 71, but not 4,000. Your research will seek to explore relationships between data sets. In order to conduct research, you have to identify the relationship between data sets. To do that, you must ask yourself which data set could influence the other. This comes from your research question. What is the potential relationship you wish to study and what is your hypothesis? This is where independent and dependent variables come into play. An independent variable is the variable which will be manipulated by the researcher. And a dependent variable is the variable which will be affected by the research study. What that means is, we believe a change in one variable will show a change in another variable. By changing the independent variable, we expect to see a change in the dependent variable. But if we were to reverse it, meaning if we were to run the research in the opposite direction, we would not see the same change. Let's look at an example. If you want to see the effect of family income level on a student's likelihood to graduate from college, you'd be looking at two variables... income level and graduation rates. The independent variable is income level because in this question, we believe that an income change will result in a graduation rate change. This makes graduation rate the dependent variable since the graduation rate is not manipulated by the study, but rather its output. The study expects that if we look at different income levels we will see different graduation rates. The cause of childhood income level creates a college graduation rate effect. If we were to run the opposite study, however, we would be unable to because college graduation rate would not be able to affect childhood income level. Let's look at one more example. If you want to increase test scores in a school, and had developed an after school program to provide assistance, you would be running an experiment. So your research question would look something like... How does an after-school intervention affect test scores at a local school? Here the independent variable is the after-school program and the dependent variable would be the test scores. The addition of the after-school program is the manipulation of the research and the output is the test score. The independent variable will cause the change in your dependent variables. You will see how the dependent variables relate to a manipulation of the independent variable. This cause and effect relationship is at the heart of quantitative research.

Contents