Because of coronavirus, there are lots of articles talking about science and how the studies being done affect everyone right now. But not everyone who writes these articles are scientists. This doesn’t mean what they write isn’t accurate, but sometimes some key points in what the study is about aren’t mentioned. Additionally, not everyone who reads these articles are scientists, which can create the spread of incomplete ideas and misunderstandings.
Here are some things you need to understand about science articles and what to think about after reading them.
What do the statistics mean?
Even if you haven’t taken a statistics course, you have at least heard the terms statistically significant and correlated. Since you will not be tested on this at the end of this article, I won’t explain how each of these are calculated, but you should at least understand what the terms mean.
Statistical significance is basically saying the results of a study aren’t by chance and the generally accepted value is .05, which means there is a 95% chance the results are actually happening in the overall population the study is looking at. That number can change depending on what the study is about and what field of science is doing the study.
Correlation in the basic form is how one thing relates to another. It establishes that the variables are related to each other and the closer that number is to -1 or 1 determines how strong that relationship is.
The reason these two terms are the ones to focus on is because these can be misunderstood without actually understanding what the study’s procedure was. Statistical significance can be misinterpreted as the effect must be real when the sample the statistic was done on isn’t representative of the population or it just happened that under those special conditions of the study the effect was able to be shown in the data. For correlation, it only looks at two variables meaning that there can be a third factor that wasn’t accounted for by the scientists. This is also why correlation doesn't equal causation because while robberies and ice cream sales are correlated, they don’t cause each other (in case you’re wondering, it's the hot weather that causes the increase in both).
How are most science articles written?
It isn’t a guarantee that the reporter read the whole study including procedure and statistical method. They could have only read the abstract of the paper (a brief summary at the top of scientific papers that go over important methodology and conclusions). This means that there is a lot of room for misinterpretation of what the results mean and how the study was done to get the results it did.
In no way is this how all science articles are written but it is a possibility so people need to be cautious of what they’re reading on their feed.
What should you be reading?
No, this isn't a promotion for one news site over another. Most journalists working in reporting the science of this whole situation are doing the best they can. What you should be reading is multiple sources. Almost every article that references a study has linked the actual peer-reviewed study. That means the study has been read over by other people in that field of study to check for inaccuracies or major flaws within the overall study’s design so when the study gets published, it has been approved by others. Read over the introduction and the discussion of the paper and get a better idea of the limitations the researchers saw within their own study. If that is too intimidating, read other articles from different news institutions about a similar topic.
In this day and age and especially in the ongoing situation, people need to be able to interpret and understand the science they are reading.