Skepticism
Skepchick Quickies, 8.12
- Update on the Simon Singh libel case with the British Chiropractic Association. (Thanks to Emory.)
- Exploring the evolutionary purpose of art.
- New study suggests that mothers, but not fathers, follow their own moms’ parenting practices.
- Five easy lies: a study in graph tweaking.
This is an ongoing , very frustrating, saga.
Is there anything WE can SPECIFICALLY do to help Simon?
That’s just scratching the surface of what you can do with graphs…
My favorite is a popular tactic for making a trend look more profound than it it: creative choice of Y axis values. Does showing Y from 0 to 100 make the curve slope too gentle? Make the Y axis go from 95 to 100 instead. Curve slope increased by a factor of 20!
It’s amazing how often to you see that one.
I’m pretty sure my wife is planning to abandon her mother’s parenting practices.
Which makes me wonder if the results of the study are due in part to the presence of the grandmother.
@halincoh: I’ve been trying to follow this, but I have to agree with halincoh, are there any ways we can support Simon with funds if necessary?
@TheCzech: I noticed that one was missing too.
I also think I remember some anti-vaxers using the rate of the rate argument for why we didn’t see a drop in the incidence of autism after thimerosol was removed. That said, I actually see a bit of this within the scientific community- there it’s extremely disappointing.
@TheCzech:
I’ve also seen it the other way around, where the Y-axis is increased to make the trend look more stable. The sad thing is, a lot of people fall for it. I have a coworker who will often spend over 20 minutes adjusting the color scale and zoom level on a 3D graph until it looks good. He doesn’t seem to realize that the data is exactly the same and he’s not actually getting better date because the graph looks nicer.