Profile picture
Louis Harreau @Louih73
, 26 tweets, 10 min read Read on Twitter
Let’s have *the talk*.
I know you are already in full Christmas mode, but we need to talk about #Draghitieguesses
We made a comprehensive analysis of this phenomenon: the idea is to validate the theorems 1 and 2
And to help you for the game (3). A basic analysis of social networks validate the (4)
But before, a little epistemology of the phenomenon: the #Draghitieguesses has been created in April 2014 by @katie_martin_fx even if there are proofs that Draghi has been wearing ties way before that date
The game got its lettres de noblesse when the ECB spoiled it and acknowledged it in 2014
Surprisingly we look at the best scientific based about monetary policy and we could not find any analysis about the impact of Draghi ties
So we made our own analysis, we use this database (already published on this website)
We use natural intelligence, human learning, data handicraft and small data to build this smart database: we numérise the compris of the ties into RGB
We also create in-house indices, but that’s mostly to use Greek letters (we think that it increases the credibility of our analysis)
And also because @Zohra_1992 wanted absolutely to create indices
Before entering into the statistical analysis, let’s have a step back and look at our data:
1) the ties are always on a white shirt and a dark suit: we exclude other situations like:
2) Draghi has a limited range of colours, contrary to the benchmark: Merkel
3) we know that we have a favorite one and we have to keep it out of our paper, as said one of Draghi’s thesis supervisor
Now let’s enter into the hard part: how to forecast the tie (how to win at the #Draghitieguesses game)
1) you can bet on the most frequent ties and exclude the low frequency ones
2) you can bet on a new tie after Draghi’s birthday or after Christmas
But beware: Draghi taste in ties is changing: on average half of his ties are blue, but recently, the blue ties are less frequent
We even identify a Vomiting Camel formation(here too, thanks @katie_martin_fx ) on the deep blue colour, whereas there is a bevel formation for the deep wine ties. It probably means something
And so we don’t have a clear view on what to bet for the #Draghitieguesses game (and we don’t want to spoil the game anyway)
Then we ran a lot of regressions versus the bund, the EUR and the swap Eonia (@Zohra_1992 made the job, I take the credit) and our conclusions are:
1) econometrics is not our thing
2) there is no correlation between the colour of the tie and the market impact
We still achieve to have a result that has some kind of meaning: a blue tie has a stronger market impact (ie more volatility) but that’s obviously after a hard work of distorting the data to@get a result
So our conclusion is that the hypotheses are wrong (sorry, I know it’s hard to read, but you need the truth)
However, we open the discussion and we suggest further research in this field:
1) what about Draghi bow ties?
2) what about the shape of the knot? (We assume that a Windsor is hawkish and a four-in-hand is dovish)
That was long, absurd and totally useless, we know that. On top of that we couldn’t find any exploitable result (for the #Draghitieguesses or for the markets).
Now the question is why are people interested in the clothes of a central banker, a small civil servant, a technician?
And our answer is that Draghi filled the lack of leadership in the Eurozone, he was the only one legitimate, capable and empowered enough to take the lead and put an end to the Eurozone crisis.
And he will leave in October 2019. (end)
Missing some Tweet in this thread?
You can try to force a refresh.

Like this thread? Get email updates or save it to PDF!

Subscribe to Louis Harreau
Profile picture

Get real-time email alerts when new unrolls are available from this author!

This content may be removed anytime!

Twitter may remove this content at anytime, convert it as a PDF, save and print for later use!

Try unrolling a thread yourself!

how to unroll video

1) Follow Thread Reader App on Twitter so you can easily mention us!

2) Go to a Twitter thread (series of Tweets by the same owner) and mention us with a keyword "unroll" @threadreaderapp unroll

You can practice here first or read more on our help page!

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just three indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member and get exclusive features!

Premium member ($30.00/year)

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!