25 Confounding Variable Examples

confounding variable example and definition, explained below

Confounding variables are variables that ‘confound’ (meaning to confuse) the data in a study. In scholarly terms, we say that they are extraneous variables that correlate (positively or negatively) with both the dependent variable and the independent variable (Scharrer & Ramasubramanian, 2021).

These variables present a challenge in research as they can obscure the potential relationships between the variables under examination, leading to spurious correlations and the famous third variable problem.

Accurately isolating and controlling confounding variables is thus crucial in maximizing the validity of an experiment or study, primarily when trying to determine cause-effect relationships between variables (Knapp, 2017; Nestor & Schutt, 2018).

chrisAn Academic Definition: “A confounding variable is one whose effect on the dependent variable could be mistaken for the effect of the independent variable.” (Boniface, 2019)

Confounding Variables Examples

1. IQ and Reading Ability
A study could find a positive correlation between children’s IQ and reading ability. However, the socioeconomic status of the families could be a confounding variable, as children from wealthier families could have more access to books and educational resources.

2. Coffee Intake and Heart Disease
A research finding suggests a positive correlation between coffee intake and heart disease. But the variable ‘exercise’ could confound the situation, as those who drink a lot of coffee might also do less exercise.

3. Medication and Recovery Time
A study posits a link between a specific medication and faster recovery time from a disease. However, the overall health of the patient, which can significantly affect recovery, serves as a confounding variable.

4. Unemployment and Mental Health
There seems to be a relationship between unemployment and poor mental health. However, the confounding variable can be the quality of the support network, as unemployed individuals with robust emotional support might have better mental health.

5. Exercise and Stress Levels
A study might show a negative correlation between exercise levels and stress. But, sleep patterns could act as a confounder, as individuals who exercise more might also have better sleep, which in turn could lower stress levels.

6. Height and Self-esteem
A study claims a positive correlation between height and self-esteem. In this case, attractiveness can confound the result, as sometimes taller people might be judged by society as more attractive, leading to higher self-esteem.

7. Class Attendance and Grades
Research indicates that students who attend classes regularly have better grades. However, a student’s intrinsic motivation to learn could be a confounding variable, as these students might not only attend class but also study more outside of class.

8. Age and Job Satisfaction
A study might suggest that older employees are more satisfied with their jobs. In this scenario, job position could be a confounder, as older employees might occupy higher, more gratifying positions in the company.

9. Light Exposure and Depression
Researching seasonal depression might show a connection between reduced light exposure in winter and increased depression rates. However, physical activity (which tends to decrease in winter) could confound these results.

10. Parent’s Education and Children’s Success at School
A study states that children of highly educated parents perform better at school. However, a confounding variable might be the parents’ income, which could allow for a range of educational resources.

11. Physical Exercise and Academic Performance
A positive correlation may be found between daily physical exercise and academic performance. However, time management skills can be a potential confounder as students with good time management skills might be more likely to fit regular exercise into their schedule and also keep up with their academic work efficiently.

12. Daily Screen Time and Obesity
Research suggests a link between extensive daily screen time and obesity. But the confounding variable could be the lack of physical activity, which is often associated with both increased screen time and obesity.

13. Breakfast Consumption and Academic Performance
It might be suggested that students who eat breakfast regularly perform better academically. However, the confounding factor could be the overall nutritional status of the students, as those who eat breakfast regularly may also follow healthier eating habits that boost their academic performance.

14. Population Density and Disease Transmission
A study may show higher disease transmission rates in densely populated areas. Still, public health infrastructure could be a confounding variable, as densely populated areas with poor health facilities might witness even higher transmission rates.

15. Age and Skin Cancer
A study might suggest that older individuals are at a higher risk of skin cancer. However, exposure to sunlight, a major factor contributing to skin cancer, may confound the relationship, with individuals exposed to more sunlight over time having a greater risk.

16. Working Hours and Job Satisfaction
A hypothetical study indicates that employees working longer hours report lower job satisfaction levels. However, the job’s intrinsic interest could be a confounder, as someone who finds their job genuinely interesting might report higher satisfaction levels despite working long hours.

17. Sugar Consumption and Tooth Decay
Sugar intake is linked to tooth decay rates. However, dental hygiene practice is a typical confounding variable: individuals who consume a lot of sugar but maintain good oral hygiene might show lower tooth decay rates.

18. Farm Exposure and Respiratory Illness
A study observes a relationship between farm exposure and reduced respiratory illnesses. Yet, a healthier overall lifestyle associated with living in rural areas might confound these results.

19. Outdoor Activities and Mental Health
Research might suggest a link between participating in outdoor activities and improved mental health. However, pre-existing physical health could be a confounding variable, as those enjoying good physical health could be more likely to participate in frequent outdoor activities, thereby resulting in improved mental health.

20. Pet Ownership and Happiness
A study shows that pet owners report higher levels of happiness. However, family dynamics can serve as a confounding variable, as the presence of pets might be linked to a more active and happier family life.

21. Vitamin D Levels and Depression
Research indicates a correlation between low vitamin D levels and depression. However, sunlight exposure might act as a confounding variable, as it affects both vitamin D levels and mood.

22. Employee Training and Organizational Performance
A positive relationship might be found between the level of employee training and organizational performance. Still, the organization’s leadership quality could confound these results, being significant in both successful employee training implementation and high organizational performance.

23. Social Media Use and Loneliness
There appears to be a positive correlation between high social media use and feelings of loneliness. However, personal temperament can be a confounding variable, as individuals with certain temperaments may spend more time on social media and feel more isolated.

24. Respiratory Illnesses and Air Pollution
Studies indicate that areas with higher air pollution have more respiratory illnesses. However, the time spent outdoors could be a confounding variable, as those spending more time outside in polluted areas have a higher exposure to pollutants.

25. Maternal Age and Birth Complications
Advanced maternal age is linked to increased risk of birth complications. Yet, health conditions such as hypertension, more common in older women, could confound these results.

Types of Confounding Variables

The scope of confounding variables spans across order effects, participant variability, social desirability effect, Hawthorne effect, demand characteristics, and evaluation apprehension, among other types (Parker & Berman, 2016).

  • Order Effects refer to the impact on a participant’s performance or behavior brought on by the order in which the experimental tasks are presented (Riegelman, 2020). The learning or performance of a task could influence the performance or understanding of subsequent tasks (experiment with multiple language assessments: German followed by French, could have different results if tested in the reverse order).
  • Participant Variability tackles the inconsistencies stemming from unique characteristics or behaviors of individual participants, which could inadvertently impact the results. Physical fitness levels among participants in an exercise study could greatly influence the results.
  • Social Desirability Effect comes into play when participants modify their responses to be more socially acceptable, often leading to bias in self-reporting studies. For instance, in a study measuring dietary habits, participants might overreport healthy food consumption and underreport unhealthy food choices to align with what they perceive as socially desirable.
  • Hawthorne Effect constitutes a type of observer effect where individuals modify their behavior in response to being observed during a study (Nestor & Schutt, 2018; Riegelman, 2020). In a job efficiency study, employees may work harder just because they know they’re being observed.
  • Demand Characteristics include cues that might inadvertently inform participants of the experiment’s purpose or anticipated results, resulting in biased outcomes (Lock et al., 2020). If participants in a product testing study deduce the product being promoted, it might alter their responses.
  • Evaluation Apprehension could affect the findings of a study when participants’ anxiety about being evaluated leads them to alter their behavior (Boniface, 2019; Knapp, 2017). This is common in performance studies where participants know their results will be judged or compared.


Confounding variables can complicate and potentially distort the results of experiments and studies. Yet, by accurately recognizing and controlling for these confounding variables, researchers can ensure more valid findings and more precise observations about the relationships between variables. Understanding the nature and impact of confounding variables and the inherent challenges in isolating them is crucial for anyone engaged in rigorous research.


Boniface, D. R. (2019). Experiment Design and Statistical Methods For Behavioural and Social Research. CRC Press. ISBN: 9781351449298.

Knapp, H. (2017). Intermediate Statistics Using SPSS. SAGE Publications.

Lock, R. H., Lock, P. F., Morgan, K. L., Lock, E. F., & Lock, D. F. (2020). Statistics: Unlocking the Power of Data (3rd ed.). Wiley.

Nestor, P. G., & Schutt, R. K. (2018). Research Methods in Psychology: Investigating Human Behavior. SAGE Publications.

Parker, R. A., & Berman, N. G. (2016). Planning Clinical Research. Cambridge University Press.

Riegelman, R. K. (2020). Studying a Study and Testing a Test (7th ed.). Wolters Kluwer Health.

Scharrer, E., & Ramasubramanian, S. (2021). Quantitative Research Methods in Communication: The Power of Numbers for Social Justice. Taylor & Francis.

Website | + posts

Dr. Chris Drew is the founder of the Helpful Professor. He holds a PhD in education and has published over 20 articles in scholarly journals. He is the former editor of the Journal of Learning Development in Higher Education. [Image Descriptor: Photo of Chris]

Leave a Comment

Your email address will not be published. Required fields are marked *