Popular Posts

Caveat Emptor

The opinions expressed on this page are mine alone. Any similarities to the views of my employer are completely coincidental.

Tuesday, 29 November 2016

Imaginary Friends

It's a peccadillo but  I have to confess that I sometimes listen to old episodes of Desert Island Discs while I'm doing insufferably boring things like cleaning the bathroom. So at the weekend I was listening to Alison Lurie talking to Roy Plomley. 

What I've read of Lurie I  liked, though she came over on the show as uptight and humourless. No matter, it's the kind of setting  that doesn't always bring out the best in people. What surprised me though is what she had to say about Imaginary Friends

Plomley asked her directly whether the novel was based on anything in particular, or words to that effect.  Yes, she answered, it was influenced by Hawthorne's The Blithedale Romance and by Henry James' The Bostonians. OK, I can see the former and I'll take the latter on trust, but I always thought the most important influence in the everyday sense of the word was Festinger, Riecken and Schachter's When Prophecy Fails.  I mean, it's virtually a fictional retelling of the same events.

At least that's what I always used to tell my students when I was trying to fake some knowledge of ethnographic fieldwork. Maybe I was wrong or maybe she was thinking about influence in some deeper literary sense than my literal minded interpretation. Still, very odd.

Wednesday, 23 November 2016

Wednesday morning magic

Two pieces of musical magic for Wednesday morning. First up Chet Baker's Almost Blue. Chet's  doing a Miles pastiche but man can he make that horn sing. And then there is Daniel Kahn's Yiddish version of Leonard Cohen's Hallelujah. Personally I think the lyrics are better than the original. Kahn also does a nice line in Yiddish worker's songs, but I admit that might be a bit of an esoteric taste. L'chaim.

Tuesday, 22 November 2016

The class liberation officer

The Oxford Mail has been carrying a story that St Hilda's College students have appointed a 'class liberation officer'. Apparently "...people from working-class backgrounds needed support because [sic] suffered from classism while at university." They go on to quote a student who in a comment to The Sunday Times said: "Insults such as 'chav', chav-themed social nights and questions such as 'why are you wearing Primark?' can make poor students feel upset and worthless."

I can't claim any special insight into the minds of today's undergraduates since I meet so few of them, but I can't help thinking that previous generations were made of sterner stuff. Working class students were very thin on the ground when I was an undergraduate but generally we found much more pressing things to feel upset and worthless about, like third-world poverty, nuclear Armageddon and failed love affairs.

And as for our clothing, well that was a competition to see who could wear the most proletarian gear possible. Combat jackets, donkey jackets, Doc Maarten boots, shoes full of holes,  army surplus jumpers and shirts, jeans that looked as though they hadn't been washed for 5 years. I spent a year wearing a lumberjack coat with an acrylic fleecy collar purchased when I was 13 from C&A. Nobody batted an eyelid and I only threw it away because the arms got ridiculously short  and I could'nt do the zip up any more!

Primark? We used to dream of Primark!

William Trevor RIP

So Farewell
William Trevor Cox.

You wrote
Death in
But you died in

Fool of Fortune.
Keith's mum
Said you should
Have a Nobel.

But they gave
It to Dylan.

And now you
Blowin' in the wind.

E. J. Lundqvist 98¾

Wednesday, 16 November 2016

Sartre on class

"Les classes ne sont pas, on les fait"." This seems to me to be right in various ways, not all of which may have been intended by Sartre. I'm guessing it comes from Critique de la raison dialectique but I doubt I'll be reading it soon to find out.

Tuesday, 15 November 2016

UK earnings inequality: the view from ONS

A functioning democracy needs good quality economic and social statistics. Politicians may have an easier life in a post fact world but we, the citizens, shouldn't let them get away with it. An important part of holding our elected representatives to account is the existence of a well functioning organization, not under direct government control,  tasked with the production of high quality statistical information. That is what ONS is supposed to be.

It's been common knowledge  that things at ONS have not been going so well. The move out of London to Newport resulted in a significant loss of expertise that has been difficult to replace and the Bean report  confirmed what everyone had long suspected. Yesterday I saw a stunning illustration of just how bad things have gotten.

For reasons that I won't go into I wanted to know the mean and standard deviation of full time earnings in the UK. Let's leave aside the fact that the standard deviation of an earnings distribution is not an especially sensible thing to be inquiring about. I doubted that I would easily be able to find the information, but as always I cheerfully Googled and was surprised to find that I was not the only one with this strange interest.  In March 2014 a certain  Mr Travers made a FOI request to ONS asking for the mean and standard deviation of annual salaries in the UK. Even better ONS provided him with the information and you can see their response on their website.

Great, I thought. That was easy. Then I started looking at the numbers. They come from the Annual Survey of Hours and Earnings (ASHE). In 2012-13 the mean earnings of a full-time employee in the UK was about £33,000 which looks plausible. In fact from other sources I know that the median in that year was around £27,000.  Then I looked at the estimate of the standard deviation. Oh dear. ONS expect Mr Travers to believe that the standard deviation is £133. That implies a coefficient of variation of about 0.004 or a Gini of roughly 0.002 (the current Gini for income in the UK is about 0.34). If you take this seriously you reach the conclusion that UK is the most equal society in recorded history.

How can it be that even in its emaciated state our national statistical agency employs people to communicate with the public that  have no  feeling for the correct orders of magnitude of the numbers they deal with? OK, maybe it was delegated to the dimmest of the interns or maybe it was a Friday night rush job, but my guess is that nothing normally gets out of ONS before it is signed off by a more senior supervisor who you would expect to know better.

It's easy to make mistakes with numbers,  I know because I make them all the time (but mostly spot them before I embarrass myself) but ONS should do better. They owe it to us and we have a right to expect it. In a world where populist politicians get off on denigrating experts making mistakes like this is another small step towards the new age of darkness.

Friday, 11 November 2016

Leonard Cohen RIP

So long
Leonard Norman Cohen.

Poet, singer, melancholic.


You were
The favourite game
Of the beautiful losers.

But now it's game over.

W. B. Yeats 11 ¾

Thursday, 10 November 2016

Legitimate concerns

On the first Wednesday after the first Tuesday after the first Monday in November 1980 I was sitting in Bob McKenzie's Political Sociology lecture  listening to him assure us that though the election of Ronald Reagan seemed like the end of the world it probably wasn't going to be as bad as we feared. The gist of his argument was that although Reagan was a fool, he at least was a lazy fool  who had just about enough sense to appoint competent people to his cabinet and to hire advisors who actually  knew something about the world. 

As things turned out he  got it broadly right. The course of events was not particularly edifying but things could have turned out a lot worse. I'd like to believe something along those lines today. But I'm not confident I can. For sure the sun will rise tomorrow, but come January we may be looking at a much uglier world.

So what's to be done? Well firstly not to go off on a self-righteous bender. I heard an emotional Simon Schama on the radio yesterday saying that Trump is a fascist. This is nonsense. His "ideas" aren't coherent enough to be sensibly described in that way. He's certainly a ruthless bigot, but that isn't quite the same thing. I don't think that Trump has an ideology of any kind other than whatever serves to promote his infantile ego. But that is besides the point. Narcissism among politicians is just a matter of degree. Trump is actually heir to a much more native tradition, that of Huey Long, champion of the small guy against the establishment. They share the same  mixture of crude populist rhetoric and  authoritarian instinct. The main difference is that Long actually did achieve something for his constituency while all that Trump will do, if he has his way, is make them poorer, more disillusioned, more angry.

What I'm pondering is the response of the liberal-left  in America to Trump and in Britain to Brexit. And all the while I hear the same phrase: "we have to respond to the legitimate concerns of...". But what if these concerns are not, in fact, legitimate? What if they are incoherent or  unintelligible? What if behind the rage is just a toxic soup of muddle, misinformation, fantasy, incompatible wishes and yes, racism, fear, envy, xenophobia and nostalgia for a past that never happened? How are you going to address the "legitimate concerns" of someone who wants to close the border to all wage undercutting foreigners, put the names of foreigners who are already here on a list and restrict their  access to health care, education and other public services, who at the same time wants that nice Polish lady to care for his demented mother (without it costing too much),  a cheap car, cheap electronic goods  and protection from foreign competition? Yes day to day politics is about compromise, but as Weber pointed out  politics is also about ultimate values and sometimes you come to a point where to compromise means either pretending that 2+2=5 or even worse just giving up even pretending to pursue the things that made the game worth playing in the first place.

"Legitimate concerns" are not just things that are given. They are created. It's too simplistic to blame their creation just on the tabloid media. But certainly the constant drip of poison, albeit into the mouths of people who already have a taste for it, doesn't help. What the liberal-left lacks is a strategy to aggressively shape the terms of the debate rather than simply go along with what they are too eager to accept as given. They've forgotten that politics isn't just about what people in Westminster believe and know. Sometimes you have to dare to tell people that they can't have all the good things they want and that anyone that promises them is a charlatan and a fraud. Sometimes you have to tell them that their gut instincts are wrong and unworthy of them. Sometimes you have to tell them that what they say they want will actually make them and every one else poorer and less happy than they otherwise would be. And you have to persuade them without patronizing them. 

It's a big ask. But all the alternatives look worse.

Thursday, 3 November 2016

Heteroscedastic Park

When I taught at the Essex Summer School they produced every year a souvenir T-shirt. One year it, must have been in the early 90s, the T- shirt had a cartoon of a dinosaur wrestling with some Greek symbols and the legend Heteroscedastic Park.  I always wondered who came up with it: I bet most of the students and  even some of the faculty didn't  get all of the joke. 

Which is all in aid of saying that I've put some STATA code up on my web-site (scroll to the bottom) to estimate a heteroscedastic normal pdf regression which allows predictors both for the mean and the dispersion.

If you looked hard enough there has always been code floating about to do this sort of thing. Scott Eliason has some Gauss code in his little ML book, and the old SYSTAT manuals had an example of how to do it (anyone remember SYSTAT?). More recently Bruce Western and Deirdre Bloome discuss this sort of model and provide code in their Sociological Methodology piece. I thought their code, which as far as I can see works fine, was a bit involved, so I've written something simpler and more direct.