This page has been archived and commenting is disabled.
"Something Disquieting Is Afoot" For U.S. Bond Markets
Submitted by Salil Mehta via Statistical Ideas blog,
We replicate a previous chart showing extreme daily moves in the U.S. stock market. This time though, we focus on U.S. bonds and show that something disquieting is afoot. As we approach this month's well anticipated Federal Open Market Committee meeting, market participants are interested in knowing what acceleration there might be going into year end, in extreme bond volatility.
We see some kinship with the stock market chart linked above. Namely that during the global financial crisis, there was a dramatic uptick in market gyrations (both up and down). At a high-level, this is where the commonalities disappear. The two charts are otherwise probabilistically different (>90% significance on a few nonparametric model fits) than one another. By way of reference, seeing greater than a 0.5% daily move in the bond markets (in either direction, and as proxied by the Vanguard total bond market index), or seeing greater than a 2.0% daily move in the stock market accounts for ~8% of all trading days (over 9 years or more than 2200 trading days) in each of their respective markets. Or roughly a 4%-5% tail risk - since for stocks and surprisingly not for bonds there is actually a slight wider tail on the losing end of the distribution versus the gaining end. Notice in the chart above, a more balanced split between years where there are more extreme down-days versus years where there are more extreme up-days?
Now we show the extreme moves for both assets, jointly, in the chart below. Grey for stocks, and pink for bonds. One can appreciate that in a respectable recent bulk of the 9-year history, 2010 on through 2014, the probability relationship (between extreme risk for bonds and for stocks) entirely dissolves!
We essentially have some false starts, where there is a risk surge in one asset class but not the other (e.g., 2013). But we know that when a catastrophe in the markets occur, as we saw on Black Monday, we only need one asset class in distress (not multiple). And when things move fast, it could be difficult to stay ahead of the loss measures. Bonds too, which at that time moved only a fraction in magnitude relative to equities are hardly a diverse shelter from the storm. Note that there were no extreme moves in bonds overall during all of July and August 2015, and only 2 extreme moves in all of 2012 (both to the downside) despite the major Greece debt downgrades inspiring global markets' havoc!
But now as we end 2015 we still notice that things are different. Both stocks and bonds have seen a pick-up in their frequency of extremely volatile days (in both directions). There is no certainty that things are not destabilizing in both markets, jointly. Advanced algorithms can detect a probabilistic cluster that includes the rise in risk during 2007 as a similar year (along with a couple other years). And we know what happened in the year following 2007.
Clearly this pattern of looking at higher risk in both major asset classes (bonds and stocks), leading to momentum in at least one asset class, isn't a sure thing. Nothing is, but there is a high probability relationship that tilts the odds in favor of soon having a bout of extreme risk (correlation of 0.5). The analogy is as if you notice an ember smoldering in a combustible forest you might be only somewhat cautious, perhaps even rationalizing it away. But if you then notice a second ember smoking up...
»
- 18 reads
- Printer-friendly version
- Send to friend
- advertisements -
JSTFU and BTFD
0.5 correlation is no correlation AT ALL.
1.0 is perfect correlation and 0.0 is inverse correlation.
Chart shows NOTHING
No, 1.0 = high positive correl
-1.0 = high negative correl
0.0=no correl
Um, just no.
-1.0 is inverse correlation. And 0.0 is no correlation at all.
But you're right that 1.0 is perfect correlation.
1 out of 3 ain't bad.
Except it is.
I missed maff that day due to climate change.
---Anonymous Economist
In other words, you wet the bed again.
And if you get a 'perfect correlation' of 1.0 or a 'perfect inverse correlation' of -1.0, that means that the researcher/statistician likely cheated/fudged their data which means that you now have to look more closely at the actual research in question. Perfect correlations are suspect, and rare.
Or more likely, you are measuring the same thing as opposed to independent things. Like the 0.95 correlation between the seperate "asset classes" US stocks and global stocks.
There's not a high degree of correlation between those asset classes. They're the same thing...
Of course it shows something. It shows you don't know what the fuck you're talking about.
Hey, get your ass back into chat, motherfucker.
Make that doubly get your ass back into chat.
nopat! The chat heathens are out of control and know not of financial innovation and other assets to humanity that banksters provide! Please come school these financial savages!
So the Syrian who drove Nopat out of his home in CHAT now asks for him to come back after he has thoroughly ruined chat. What do you expect from Islam.
Nopat, bay and luck want you to come back, I guess they want to finish you off after stabbing you in the back last time. Dont end up like an ISIS captive in the chumba chat caliphate.
No, if anyone drove him out of chat, it was posters like you COSMOS...ya fuckan douche bag.
The guy with the terrorist ISIS beard talks.
We're missing the element of the statist banker in chat. Get your ass in here.
Hear hear! Nopat all is forgiven, and you are welcome back it chat any time!
No seriously, it's gotten real weird since you left. Luck won't stop talking about his kingdom of chickens, thistooshallpass has been trying to doxx everyone's weed stash, pob won't shut the fuck up about his taters, truxton, chump and prawn have all joined The Crips and won't stop threatening everyone, Main Sequence has threatend to join The Fed because Bay of Pigs won't lend him $2, Don'tGive has been recruited by his local Wolverine's chapter, II and Prez gave everyone finger herpes and chumba's still alive.
Come on now 44, you know I'm not that cheap.
And no pat...yes, I agree, we miss your slanted, pro FED/Wall St point of view.
Haha, no.
Yeah, what they said. Don't be such a prude, dude. This is not your true nature.
Yeah that's it... keep talking him out of the bunker. Then BAM, we're doxxing his bunker... oh shit did I just type thi [redacted]
nopat ... Welcome back ... show up in the chatroom man !
We need some antagonism ! Idea Exchange ....
Maybe even some feedback onto data Modeling ...
Disquieting, so that's what it is. And here I thought we were getting ready for a drain pipe colonoscopy......
Something triggered a US/EU market hiccup at 11:00ish?
Run like hell.
To Where?
Over the cliff of course......
Please, when it comes to soveriegn debt/bonds, there is no "market" only central bank manipulation.
stupid analysis without showng all central bank balance sheet holdings.
In other news:
The Senate just replaced “no child left behind” with “everyone will be left behind”.
My translator says that the bill's title is actually "No one is allowed to be left behind when we crash".
Maybe I'm looking at an earlier version. Potato- Potahto.
Youtube pundits say Yellen will + rate 1/4.
I think it would make for very good entertainment if she raised it 2%. The expressions on pretty much everyone's faces would be priceless.
Hello, 911? Please help me. There's a banker in my house!
so btfd then?
domn't forget the caps BTFD
Imagine how large the U.S Debt would be without ZIRP.
Our monitization of the debt, and destruction of the currency does have some benefits!
What's funnier is, how our creditors stand for it!!! LOL!!!
Aside from the middle-class, guess who the real sucker is!
Merry Xmas Beeyoches, this market decline is just a tease, if it breaks 2000, I will hold a press conference and raise up my skirt.
Imagine how large the U.S Debt would be without ZIRP.
Our monitization of the debt, and destruction of the currency does have some benefits!
What's funnier is, how our creditors stand for it!!! LOL!!!
Aside from the middle-class, guess who the real sucker is!
Merry Xmas Beeyoches, this market decline is just a tease, if it breaks 2000, I will hold a press conference and raise up my skirt.
Without ZIRP, the US national debt would be 0.
And there would be some really pissed gangsters and oligarchs with safe deposit boxes full of papiere de toilettes.
Indeed, also imagine if .gov used accrual accounting like a business. That number is staggering (around 65 tril) and is beyond our ability to repay . . . same can be said about Japan's and soon enough the EU debt. This may be telling that a big reset will take place at some point . . .
i feel pretty sure we will get some negative rates at the short end, and the fed with raise 1/4 point in order to foster some confidence that NIRP is only temporary and that they won't allow rates to officially settle at negative yield, in other words they will raise rates to keep them from falling (this is how it will spin anyway) a 1/4 plus a 1/4 minus its not much of a difference. the fed can do two things at once, Janet is supergirl, she can do QE and raise rates, these things are not mutally exclusive, some people think of the old fed, the greenspan fed as this machine committed to incremental changes in longterm policy, while greenspan would raise rates he would also open the repo window to provide liquidity, now the repo window is so yesterday. conventional thought on what the fed can do is very stultfied, 2008 should have proved to you all that they will do MOAR than it takes, so while a small group of bloggers is yelling shennigans the fed will break new ground, and how does a professional investor react? do you jump out the window, or go with the flow. you go
Please wake me when it all finally goes BOOM! Until then......Zzzzzz.
Sleep lightly, take breakables off the shelves, and wear ear plugs. The big one is coming, soon.
I appreciate the spirit of the exercise, but I'm left...wanting. I don't want to shit too heavily on him since he could be an undergrad and this could be a good learning experience. Far be it from me to want to discourage someone's education.
My whole gripe is that I have no clue as to what question he's actually answering. There's some initial inquiry about EOY effects in various markets, but this is all annual data showing loose annual correlations between equities and bonds using a seemingly arbitrary criteria to define "extreme events." Time-varying correlations, risk premia, impacts of policy decisions, institutional effects of these markets, etc etc blah blah blah have all exhaustively been discussed. Ad nauseum. Here he's just counting days over the course of a year, and not even over what I think many would consider a representative sample (given the availability of data in these markets), considering you have this massive fucking blip in 08. In short: this is pretty fucking weak and tells me nothing.
I know this place is a veritable church of confirmation bias, but can someone at least /read/ these things before posting them?
The bottom line is we are unchartable territory.
You can run a compass heading until someone fucks with what's actually north and what's south and then you might as well throw the compass overboard and rely on pure instinct. For the most part traditional chart analysis has about as much value today as a compass in a non magnetic world. Which is to say you'll get into more problems believing in faulty instruments than none at all.
DISQUIETING I SAY!!!!!!!!!!!!!!!!!!!!!!