Skip main navigation

New offer! Get 30% off your first 2 months of Unlimited Monthly. Start your subscription for just £29.99 £19.99. New subscribers only. T&Cs apply

Find out more

How to interpret correlations and population samples

How to interpret statistical language such as correlations and population samples.
Researchers collect data to formulate facts and uncover patterns. Measurable data can be transformed into useful statistics to form practical advice. However, statistical language can be tricky and often confusing. Sometimes a word means one thing in everyday language, but something else in science jargon. Understanding meanings of scientific terms can help us to avoid generalisations and misunderstandings. You’ve probably heard the phrase correlation does not equal causation. But what does it mean? Let’s take two variables. They may seem like they move in the same direction, and it may appear that their relationship is quite strong. But it doesn’t mean we can draw a cause and effect conclusion. So imagine summertime. In summer ice cream sales increase. Sunburn rates also increase. They are correlated.
Does it mean that eating ice cream increases your risk of sunburn? Well, no. On a sunny summer day people are more likely to go to the beach, eat more ice cream, and sunbathe, which can lead to getting sunburned. But it doesn’t mean that eating ice cream caused the sunburn. Population and sample are also important when assessing truth behind the headline. In the research the group of things that we want information about is called a population, and a sample refers to a part of the population that we want to draw conclusions from. From the previous example, we want to look at the effect of sunburn on people’s health.
It would be difficult to look at everyone on a busy beach, so researchers would take a sample and specify a research question. Good research ensures that the sample is unbiased. That means that every subject in the population has an equal chance to be picked, and no one is favoured. It is also important to assure that the sample is representative of the entire population in question, and it must be big enough to measure their effect. Remember, there will be always a sampling error as we never look at the entire population at once, so data is often presented as a range. Researchers need to consider everything from age, sex, background, health conditions, physical activity and so on.
All of that to find an answer for their research question.

Watch this video to find out why the statistical language scientists use to share their research findings and recommendations can be confusing for journalists to understand, interpret and accurately report.

This article is from the free online

Food and Nutrition: The Truth Behind Food Headlines

Created by
FutureLearn - Learning For Life

Reach your personal and professional goals

Unlock access to hundreds of expert online courses and degrees from top universities and educators to gain accredited qualifications and professional CV-building certificates.

Join over 18 million learners to launch, switch or build upon your career, all at your own pace, across a wide range of topic areas.

Start Learning now