I...I have no words Non-randomized, n=63, Control: staring at desk Active intervention: caring for plant Outcome: tiny difference in proxy of mental health Headlines:pic.twitter.com/oWUH77FvMu
You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
It's just absurd If your control is "doing nothing" and your active intervention is "doing something" IT'S NOT SURPRISING THAT YOU SEE A SLIGHT DIFFERENCE
There's also this delightful gem in the Daily Mail Statistical significance =/= practical importance A ONE POINT DIFFERENCE IN AN 80-POINT ANXIETY SCALE PROBABLY DOESN'T MEAN VERY MUCHpic.twitter.com/2fICbvO0MG
A big shout-out to whoever wrote the press release, because damn this is truly awfulpic.twitter.com/6yd8nY9O4s
Any researcher anywhere knows that this is almost certainly a meaningless study It's probably just regression to the mean (i.e. people improving just by random variation) And yet, the news is completely uncritical of this fact
As others are pointing out, there are lots more problems with this study TL:DR desk plants probably don't do very much for your anxiety
P.s. for all those asking, this particular study was funded by Mitsubishi, who as far as I know don't make houseplantspic.twitter.com/HXHhHmIxb6
Blog now out on this:https://medium.com/@gidmk/desk-plants-wont-cure-your-work-anxiety-fdf1aa4e1b1d …
I was confused for a bit. In the US, that would be a potted plant. A pot plant would be entirely different (except for the overstatement of medical utility).
There are days that I question what is deemed publishable. This is one of those days 
How did they get that P-value with that data?
I'm actually not entirely sure. The stats section of the paper is a bit muddled
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.