Is this Vox article misreporting the study findings by misusing statistical jargon?

37 Views Asked by At

In this article, the author reports that a study found that "math scores went up by 0.20 standard deviations and English scores by 0.18 standard deviations". The article further states that these findings provide support for the claim that installing air filters has very good effect on learning abilities. I'm new to statistics and have been teaching myself the basics for a few weeks now, but isn't the standard deviation just a measure of how far spread out your values are? If the standard deviations for those two distributions went up, doesn't this mean that even if air filters had some effect, they simply changed how distant individual test scores are from the mean? I tried to follow up on the study, but the Vox article links me to other article, not the paper. I'm sorry if I'm missing something here. As a beginner to stats, my first thought is that simply knowing the change in standard deviation value doesn't tell us anything about whether there was a desired improvement to our outcome goals. And just to be clear, I'm not understanding the Vox article's way of reporting, not the paper itself if any of you have read it.

2

There are 2 best solutions below

0
On BEST ANSWER

They are not saying that the standard deviation increased, they are saying that that the (average) score increased by $.2$ standard deviations... standard deviations is the unit.

So if before the average score was $10$ with standard deviation $2,$ the new average score is $10+(.2)\cdot 2=10.4.$

0
On

The statement does not say that the standard deviations raised. It says that the means raised by some fraction of the standard deviation, $\mu\to\mu+0.2\sigma$. In terms of probabilities, this difference is not very significant. To know more, you need to take into account the sample size.