Spurious correlations occur when a measured variable is plotted against itself
That sounds ridiculous! Who would do that? If that happened no one would publish it! Or would they?
One estimate is that 20% of papers have spurious correlations!
The authors and editors often don't see the spurious nature of the correlations, because the variable is plotted on both axes, but transformed in some way. For example, Grain Yield (GY) plotted against Evapotranspiration (ET) is valid (panel A), and in this case has no correlation. But when plotted as water-use efficiency (ET/GY) against GY a very strong correlation occurs.
Spurious correlations are everywhere!
Virtually any field that uses correlation type analyses has spurious correlations as a foundational aspect of the research. Consider the examples below, where the variable in red text is present on both axes causing inflation (or deflation) of the correlation coefficient. Can you find an example in your field?
Note that some random guy figured this out a few years ago, but I guess editors haven't heard of this this Karl Pearson guy, it isn't like he invented correlation coefficients or something.
Pearson, K., (1897) On a form of spurious correlation which may arise when indices are used in the measurement of organs. Proc. R. Soc. Lond. 60, 489–498.
We published on this:
Gilbert, ME. Hernandez, IPhD. (2019) How should crop water-use efficiency be analyzed? A warning about spurious correlations. Field Crops Research, 235: 59-67, https://doi.org/10.1016/j.fcr.2019.02.017