Correlation Examples in Real Life

What is Correlation?

Correlation is the statistical association between the two variables. In other words, it measures the degree or extent to which two different entities are related to each other. While conducting various researches, it is difficult to do certain experiments in laboratory settings, in this case, correlation studies are conducted. The researcher need not perform any experiment, and he/she is only required to collect the data by observing the relationships among the given variable, and then making the accurate interference out of the collected data. Correlational studies are widely used in psychology researches as various psychological factors like perception, attitude, motivation and so on are difficult to control, hence the relationship between these factors or variables can be drawn with the help of the correlation studies. The data obtained through the correlation studies are represented on the ‘scattergram,’ which is also known as the scatter diagram, scatter chart, or scatter plot. It is a type of graph that clearly represents the association between the two variables, where one variable is represented on the horizontal axis, and the other on the vertical axis. The points on this plot represent the different measurements and a trend line can be drawn from these measurements if the trend line is not clear, it means weak correlation (r is near to zero), and if the trend line is clearly visible it means strong correlation (r is near to 1). There is three possible outcomes of the correlation study, i.e., the positive correlation, the negative correlation, and the zero correlation. Let’s discuss them in detail with real-life examples of correlation.

1. Zero Correlation

A zero correlation indicates that there does not exist any relationship between the two variables. For example, there does not exist the relation between the packets of chips you ate and your marks in the last exam. A zero correlation is represented by the ‘r=0.’ Where ‘r’ is the correlation coefficient. The correlation coefficient measures direction and the strength between the two variables. If the value of r is near to the +1 and -1, it indicates that there exists a strong linear relation in the given variables, and if the value is near 0, it indicates a weak relationship. The following image represents the Scattergram of the zero correlation.

Here are some examples of the zero correlation,

Weight and Exam Scores

There is zero correlation between the weight of the student and his/her score in the exams, i.e., one can not analyse the scores a person will obtain in any exam by knowing the weight of that person.

Height and Income

There is zero correlation between the height of a person and the salary he/she earn, i.e., if you know the height of a person you can not estimate the income of that person.

Drinking Tea and Intelligence Level

There is zero correlation between the amount of tea a person drinks and his/her intelligence level, i.e., one can not assume the intelligence level of a person by knowing the amount of tea he/she drinks.

Shoe Size and the Number of Movies Watched

There is zero correlation between the shoe size of a person and the number of movies he/she has watched, i.e., one can not analyse the number of movies a person watches per year by knowing his/her shoe size.

2. Positive Correlation

When the two variables vary in the same direction, i.e., if one variable increases the other variable will also increase, or if one variable decreases then the other variable also decreases, this is known as the positive correlation. The following image represents the scattergram of the positive correlation.

Here are some examples of the Positive correlation,

Sale of Apartment and the Infrastructure

Correlation studies can help the census surveys to analyze the association of great infrastructure say big parks, open areas, and other recreational areas in the building and the nearby areas, with sales of the apartments. Of course, this is a positive correlation as the better the infrastructure the more buyers will be interested to buy apartments in that area, i.e., the more will be the sales of the apartments.

Time Spent in Meetings and Value of the Person in the Company

It can be assumed in general that if a particular person is involved in almost all of the meetings of a company then he/she is more valuable to the company. Meetings are arranged to discuss all the ideas and make strategies that can increase the success of the company, and if that particular person is involved in most of the meetings, it is high because the company trust the skill and abilities of that person and he/she is an important part of the company. This shows that there exists a positive correlation between the time a person spent in the office meetings and his/her value in the company. Well, the vice-versa is also true, one can anticipate the number of meeting he/she will have to attend in the future if he/she knows his/her value in the company. One can even analyze the designation of a particular person in the company by observing the amount of time that the person spent in the official meetings. The person can also anticipate his/her performance in the company by observing the increase or decrease in the time he is involved in the meetings.

Improvement in the Health and the Medical Dose

Correlational studies are widely used in clinical trials to understand the impact of a newly manufactured drug on patients. There exists a positive correlation if the regular dose of that drug improves the health of the patient. On the other hand, if the health does not improve or do not deteriorate then there exist zero correlation between the two variable, i.e., the health and the drug.

Boiling Point of the Water with the Increase in the Impurities

The boiling point of freshwater is different from the boiling point of water that contains impurities due to the colligative properties of the solvents. The more and more impurities will be added to the freshwater the more will be its boiling point. If you observe the increase in the boiling point of the water coming into your homes through taps, you can well imagine the quality of the water. This means that there is a positive correlation between the boiling point of the water and the increase in the impurities. Drinking water should be of the consistent quality (constant boiling point) over time, i.e., there should be zero correlation between the boiling point of the water and the time elapsed. One can find the correlation between the boiling point of the water and the time elapsed, for the different states or the countries, the one that has the lowest correlation between the two variables, i.e., the boiling water and the time elapsed wins the survey as that country is able to sustain the water quality over the time.

Height and the Weight of the Person

There exist a positive correlation between the height and the weight of the person. This means that if the person is taller then he/she is more likely to have more weight than the shorter person with a similar body structure.

Ice Cream Sales and the Weather Temperature

There exists a positive relationship between the sales of ice cream and the climate temperature. This implies that the sales of ice cream are higher in hotter weather conditions. Obviously one tends to crave the ice cream in summers more than in winters.

3. Negative Correlation

When two variables vary in the opposite direction, i.e., if one variable increases the other variable decreases, or if one variable decreases the other variable increases, this is known as the negative correlation. The following image represents the scattergram of the negative correlation.

Following are some examples of the Negative Correlation,

Sales of the Apartment and the high Cost

If the apartments of the particular building are very costly, the lesser people will be interested in buying that apartment. This means that there is a negative correlation between the sales of the apartment and the high cost of the apartment.

Wisdom and the Overestimation

You must have heard the famous quote,

With Age Comes Wisdom”

A study conducted by Frank Durgin proves this quote. In this study, the participants had to tell the approximate slant of the hill. It was found that most of the older participants were better at estimating the accurate height than the younger participants. Here, wisdom is associated with the accurate estimation of the slope of the hill. It was also found that some of the older estimates and almost all younger participants gave overestimates, hence it can be concluded that wisdom and overestimation are negatively correlated, i.e., more the wisdom lesser will be the chances to make wrong estimates or the decisions. Although this is not the case in every situation, there is a number of examples available that shows that wisdom comes with experience and not just with the age.

Time Spent Running and Body Fat

There exist a negative correlation between the time spent running and the body fat of the person, i.e., the more time the person will spend running, the lesser will be the bodyweight of the person.

Time Spent Watching T.V and Score in the Exams

There exist a negative correlation between the time spent watching television and the scores obtained by the student in the exams, i.e., the more time a student spent watching the television, the lower the scores he/she will obtain in the exam.

Correlation vs Causation

People often relate correlation with causation, but these two terms have different meanings. If one variable (predicator variable/independent variable) causes the changes in the other variable (outcome variable/dependent variable) it is known as causation. The causation can be established by conducting the experiments, wherein the independent variable is manipulated and its effect on the dependent variable is noted. The experiments are conducted in a controlled setting so as to eliminate the extraneous variables. Unlike causation, if there is a correlation between two variables we can not say that the particular variable is responsible for the changes in the other variable, it only means that there exits association between the two variables because any third variable could also be the reason for the changes in the second variable. For example, being affected by a particular virus is correlated with bad health, but this does not mean that only the virus is responsible for the bad health of the patient, there could also be the involvement of the other variables such as poor immunity, low level of exercise, or bad diet.

Strengths of Correlation

• The data obtained through the correlation studies can be easily presented in the graphical format called scattergrams, which makes it easier for the researchers to analyse the association among the different variables.

• Correlation studies are very beneficial in the researches as it allows the researchers to investigate the variables that are difficult or unethical to investigate through experiments in laboratory settings. For example, it would be illegal to conduct an experiment to analyse the impact of drinking alcohol on pregnant women or analyse the impact of smoking on lung cancer; however, researchers can analyse this with the help of a correlation study by comparing the previously available data of the given variables.

• Correlation studies allow researchers to find both the strength and the direction (positive or negative correlation) of the association between the two variables.

Drawbacks of Correlation

• The results obtained through the correlation are not much reliable, one can not assume that a particular variable is responsible for the changes in the other variables even if there is a strong relationship between the two variables due to the occurrence of the underside variables (extraneous variables) in the study. For example, In a correlation study, a positive correlation is found between the impact of watching violent episodes on television and the aggressive behaviour among adolescents; however, this may be due to other factors (extraneous variables) say growing up in a violent environment, hence both the factors, i.e., watching violence and growing up in the violent environment could be the possible variables for the aggressive behaviour.

• Correlation studies allow the researchers to find the association between the two variables, but it does provide the answer to that why this association exist? Correlation studies do not provide information regarding which variable causes the changes in the given variable. For example, there is a correlation between wealth and education, it can lead to two meanings, that the more educated the person is more will be the wealth or more wealth a person has, the more education he/she can obtain. this shows that one can not determine the causation. Moreover, any third variable could also be involved as discussed in the above point. for example, living in a developed and rich country could be the cause of both education and wealth.