Monday, 30 January 2012

Be Careful with Correlations

Hello one and all,

A friend of mine brought to my attention a blog post from Mike Webb (also a friend), arguing that there was a crisis in confidence in the UK Government. The blog post is a good attempt at rigour, but I'm afraid Mike fell into a simple trap.

The argument is expressed in detail here but I think a not unfair summary is this:

1. Uk Government yields have been closely correlated with Yields from European nations..
2. In the months leading up to May 2010, there was a steep dropoff in that Correlation
3. The most natural explanation for that is uncertainty over the outcome of the election.

Statements 1 & 2 are both true, and statement 3 seems reasonable at first glance. So I can say that I liked the blog post. I particularly liked the effort he went to to double check his findings by comparing across multiple regions - UK compared to Germany, France, Italy etc.

Unfortunately his conclusion, that there was mounting suspicion over UK solvency has only a very superficial link to the data. His predictions entail maximally that UK Government Yields climbed in these months. Minimally, his explanation entails that UK yields behaved in a way that was at odds with a wide range of countries in those months.

With a Bloomberg machine able to run correlations he checks only the correlations between different Governments' yields. Unfortunately, he doesn't bother to show us what happened to the actual yields themselves.

Here are UK Yields in the relevant time period (click on the image to see it blown up):

From the graph, we see that over the period UK yields moved up a bit, down a bit, and actually ended the period that he is referring to (January - April 2010) at about the same level, maybe a tiny bit up.

Now here are the European Yields that he is referring to:

Yes, falling yields, implying pessimism over the economy and as yet no worries about fiscal solvency.

The absence of any rise in UK yields is at least a worry for the argument that investors were getting jittery about UK solvency, Now, one could argue, I suppose: "Well, what happens if there was some, external international event that dragged those other yields down, and would have dragged UK yields down as well, if it weren't for solvency jitters?"

Well lets look outside of Europe for a moment:

Ah yes, they all went up, slightly.

In other words, the drop off in correlation he refers to is explained only by a decline in Bond Yields in European countries. One would be very hard pressed to argue that suddenly investors got jittery over UK yields- There's no actual evidence for this in the data whatsoever.

So next time you look only at correlations, remember to actually look at the things you're correlating, before you jump to any conclusions!!!

Tuesday, 24 January 2012

Scattershot Thoughts

Hello all,

Sorry I did a bit of a disappearing act there for a while, you know work happened, life happened.

Anyway, I think its about time for me to pen some thoughts about the future, what with it being the first of the month and all that, a great opportunity to pontificate & predict etc.

Well, politically of course 2012 is a big year - its election time in the States. Obama vs Romney/Gingrich/Santorum/

Well, the Republicans are doing an awfully bad job of choosing their nominee this year.

Anyway, in keeping with the spirits of this blog, which is trying to use models to predict political outcomes, we have a few different models which we can bring to bear on this:

  1. Median voter Theorem

  2. Economic Referendum

  3. The guy that's taller

So most readers of this blog will be familiar with 1. & 2., whilst 3. is the controversial theory based on the simple empirical observation that since the television was invented in the 1920s, the tallest guy has tended to win the U.S. presidential election.

Median voter theorem unambiguously predicts Obama. Obama places jobs above the deficit as his prime concern, like the majority of the population. Obama supports a balanced tax&cuts approach to the deficit, like the vast majority of the population. Obama supports action on climate change, like the majority of the American population. Obama supported the repeal of Don't ask, Don't Tell, like the vast majority of Americans. The list goes on. In fact, Obama's attempt to occupy all of the mainstream Conservative positions has been so succesful that its driven the Republican party into the fringes of its base. With a Gay Soldier being booed in a Republican debate for no reason other than being Gay. So, Median Voter Theorem definitely scores this for Obama.

The Economic Referendum theory is a bit less clear. The basic principle is that the election is treated as a referendum on how well the current president is handling the economy. Until recently, it was obvious this theory would have predicted Romney would walk away with it. However, a few tantalising hints at a recovery (but no actual recovery yet as far as I can see) would suggest that the answer is not obvious. Part of the problem is that the theory isn't as simple as "Unemployment <7% = Incumbent elected, Unemployment >7% = Challenger elected". Partly its about directional movements etc. I would say, that if the economy continues to improve and growth hits 2% +/- 0.3% then this would score it for Obama. Anything less than 1% scores it for Romney. Between 1% to 1.7% is ambiguous.

Mitt Romney is a shade taller, so the third theorem, that the taller guy always wins, would call this for Romney, by an inch.

I'm assuming Romney wins the Repub nomination, which looks likelier by the day.

Sunday, 1 January 2012


I wanted to use the new year as an opportunity to pen some random thoughts about the new year. This is, afterall a blog thats supposed to be 1/3 about trying to use models to forecast the future and then using the data to improve the accuracy of our models.

So here are some thoughts:


2011 has seen some really great additions to mainstream consumer web technology. Quora began to take off but still hasn't quite managed to make it mainstream. Google Plus exploded onto the scene but since then traffic trended downwards. Facebook continued its unabated storm to glory. Airbnb also had a break this year. Its more or less consolidated its dominant position now. Dropbox is supposedly running at a mental $5 Billion valuation! From a personal perspective, my friends have finally signed up in droves to twitter.

So, I think 2012 will be another hot year for tech startups. Facebook will IPO though, which will drive stock prices through the roof for a while before it all calms down again. The startups we come across this year will find that their success is made through their ability to forge real connections between people. Android's persistent growth will eventually begin to drive Google Plus this year I think - Google plus signups will stabilise and then begin to trend upward, slowly


Unfortunately, all economists are predicting slow growth irrespective of their school of thought. Luckily for us however, the source of that slow growth varies and so we can therefore attempt to test some of the differences in views.

  • Austrians, like Ron Paul are predicting economic catastrophe, in the form of "unexpected inflation and a collapse in the value of the dollar".
  • British Politicians across the board have been predicting anaemic growth, although for different reasons. The Labour Party Line is that the Treasury Bond yields will fluctuate with the health of the economy (bad economy = low yields, and a strong economy will see higher yields). Conservatives are saying yields will stay low provided that the economy remains on top of its deficit.