Moves in heavily shorted stocks are *extreme*. Short interest factor return (in std devs) last Friday was -2.4, Monday -3.9, Tue -5.1 and yesterday **-8.8**. Overall it's a 10 standard deviation move, giving up ~3 years of return in four days
-
Show this thread
-
Replying to @macrocephalopod
Not that current moves are at all attached to market, but can you subtract the market from these? I remember a similar death of shorted stocks in 2018 that I’m not seeing here.
4 replies 1 retweet 2 likes -
Replying to @CliffordAsness @macrocephalopod
I find it odd we continually cite standard deviations for return distributions that are clearly not normally distributed
1 reply 0 retweets 0 likes -
-
There's nothing magical about the normal distribution that means its the only distribution that you can calculate the std deviation of. As long as you have finite second moment you can calculate a std deviation just fine.
1 reply 0 retweets 0 likes -
Replying to @macrocephalopod @CliffordAsness
because if the distribution of returns isn't normally distributed it's a meaningless number. It's supposed to represent something (i.e 1 std = 68% of events, 2 = 95%, etc) but if the tails are way longer and flatter than a normal distribution the number doesn't mean anything.
2 replies 0 retweets 0 likes -
Replying to @gettingclouser @CliffordAsness
I have no idea where you are getting this from but it's completely wrong. It's only meaningless if the distribution doesn't have a finite second moment. Otherwise st dev has a perfectly sensible meaning as the square root of the second central moment.
1 reply 0 retweets 0 likes
The correspondence between std deviations and quantiles (e.g. 1 sd = 68%, 2 sd = 95% etc) is true for the normal distribution but so what? It doesn't mean you can't use the standard deviation for other distributions. Just a massive misunderstanding on your part.
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.