Apr 182008
 

I recently discovered one of the most entertaining web reads I’ve come across for ages … Bad Science which is a site dedicated to pointing out where the (mostly media) uses “Bad Science” or falls victim to “Bad Science”. The author (Ben Goldacre) is a medical doctor so most of the criticisms are in relation to medicine rather than science in general. But the debunking of rubbish media reports on (mostly) medical issues is worthwhile and done in an entertaining way.

It is interesting that many of the more foolish reports in the media have to do with bad statistics rather than bad science itself. That is I suppose not too surprising, as statistics seems to be widely misunderstood.

I have the advantage that many years ago I spent some time studying statistics, and many media reports have the effect of making my inner statistician jump up and down in fury shouting “Bullshit” over and over again. Fortunately he doesn’t shout too loudly or I’d run the risk of being shut away in a room with nice soft walls.

Statistics don’t lie, but they don’t always say what we think they do

I’m going to make use of an example relating to cannabis and an article publish by that paragon of excellent and accurate reporting, the Daily Mail. The article itself is here … scary isn’t it?

A report that has statistics that says that people who smoke cannabis have a 41% higher risk of schizophrenia, indicates that cannabis smokers are more likely to have schizophrenia than the general population. That doesn’t mean that cannabis causes mental health issues; that is an untested hypothesis. A quick uneducated guess at a number of possible reasons why includes :-

  • Cannabis use increases the risk of mental health problems (yes it is possible).
  • People with mental health problems are more likely to use cannabis than others.
  • Cannabis use makes existing mental health problems worse.
  • There is no link between cannabis use and mental health problems; the correlation is accidental.
  • The study that found a correlation between cannabis use and mental health problems is flawed and there is in fact no such correlation.

One of the biggest mistakes anyone can make with statistics is to take a link between two variables (a correlation) and assume that one variable causes another (cannabis use causes mental health issues). This is known as “Correlation does not imply causation”; stealing a Wikipedia example, there is a correlation between going to bed with shoes on and waking up with a headache. Sleeping with shoes on does not cause headaches, but drinking copious quantities of alcohol makes it more likely that you will sleep with your shoes on, and far more likely you will wake with a headache.

Apr 072008
 

I loath spam; all those unsolicited emails that advertise herbal mortgages, pills that will lower the interest rate, and all those lottery wins from places I’ve never heard of. Of course everyone else does too.

But what about emails that are “near spam” ? Say you bought something online 5 years ago from some company or other, and haven’t been near them since (nothing that was wrong, you just haven’t gotten into the habit of buying socks online). Now of course, you receive this “sock newsletter” once a month. Now perhaps you were once interested, or on a very slow Sunday you like to read about socks. Perhaps.

Of course you didn’t just buy a pair of socks 5 years ago. You’ve been buying stuff ever since, and everybody is desperate to get your email address to push virtual catalogues into your over cluttered Inbox. You could go and visit the unsubscribe links to get your address removed from each and every list out there.

But someone told you once that unsubscribe links are dangerous because they’re used by spammers to verify addresses, and besides which it would take you days to get unsubscribed from all the rubbish. And of course just occasionally you take a peek at one of the emails and it has something in it you want to know … a special offer or something.

What is needed is a way of keeping “near spam” emails under control. A central place to go to indicate your preferences (“no near spam”, “just one a day”, “as much as you want to send me”, “don’t send me those stupid messages that tell me I have to use a browser to view this email”). I’m currently automatically filtering “near spams” into a folder where I can ignore them … which is something that the sales critters who spew them out certainly don’t want!

Feb 032008
 

There is something a little odd about the Writer’s Guild Of America’s strike for a better deal on “residuals”. In fact there are a couple of odd things about it. Not that I am against what they are trying to accomplish … anyone who wants to fight the big studios for whatever reason has me at least half on their side before I’ve started to think. And what they are trying to get sounds more than a little reasonable.

The first odd thing is that the workers are trying to get a bigger share of the profits. Not a share but a bigger one! Now there are other industries where workers can sometimes get a share of the profits, but it is very rare. Now why is that ? It would seem both sensible and fair to give the workers a cut of the profits … after all profits cannot be made without workers to make a ‘product’. But perhaps the bosses are too greedy to cut their workers in.

I am sure an apologist for the corrupt capitalist system will claim that entrepreneurs deserve to be rewarded for the great risk they are taking when starting an enterprise, and that share-holders also deserve a reward for the risk they take. Maybe so, but workers also deserve some of the reward.

Of course the writers of the WGA are already more successful than many other workers; one suspects this is because they are on the “posh” side of the pool of workers. Can you imagine coal miners getting a similar deal ?

The other odd thing about the whole issue is just how much support the WGA seems to get in their strike action. The US is not the first place one thinks of as places sympathetic to organised labour. In fact you would expect to see large numbers of US citizens frothing at the mouth with outrage at cheek of the workers. Perhaps this is again something to do with how writers are perceived as opposed to coal miners ?

Or perhaps the bosses in this particular case are so widely hated that even their natural supporters in politics (the Republicans) do not want to be seen supporting them.

Jan 132008
 

‘I met the well connected, the powerful and the rich; I saw little to envy or, indeed, much to admire; we were being lionised by a class of society with which we had little in common’ — Edmund Hillary

I recently read Ian Bone’s blog (a good place to go for some fresh ideas) entry on Edmund Hillary and space exploration. I was particularly taken with the quote above, and wondered about how many ordinary people have been given a glimpse into the inside of the celebrity world and recoiled with the kind of exclamation that might pop out when you lift a foot for inspection to realise that you’ve trodden in something from the bowels of a particularly unwell dog and that it is busy climbing up your jeans towards your knee.

Note that I am not talking about those who have dived head-first into the trough of the celebrity world only to discover that there are disadvantages in being a celebrity … such as a constant ‘tail’ of paparazzi busy taking photos of you when you would rather they were taking photos of someone else. Such people almost deserve their treatment although the existence of paparazzi is a symptom of some sort of disease.

I don’t particularly begrudge those with genuine talent being rewarded for doing what they do, although one does tend to worry about a society that values someone who makes people laugh greater than someone who saves their life. But these days the celebrity world seems to be populated not only by those with some level of talent, but also by those who are famous for no real reason I can figure out. I am not talking about those whose talents run in directions I don’t like … such as business or architecture, but those who really lack any form of talent whatsoever except possibly the “talent” of picking the right people to sleep with.

Mind you the world of celebrity does seem to be heavily loaded in favour of those who are good at proclaiming how important they are, rather than with those who genuinely deserve the respect of the rest of society. Some of those in the celebrity world are there because they work in industries that thrive on publicity … I am thinking specifically of actors. Perhaps those who end up being celebrities because they are actors or musicians should try to bring more normal people into the celebrity world … those who deserve to be honoured but who are unlikely to trumpet their own worthiness.

Nov 232007
 

Today the UK’s Information Commissioner announced that today’s young (and in some cases not so young!) are putting their future careers at risk with some of their ‘riskier’ posts on social networking sites such as Facebook. In addition they pointed out that they were risking identity theft by putting so much personal information online.

It is worth mentioning that information can live online for a very long time … forever if the people behind Archive.Org have their way. This is not necessarily a bad thing although it can come as a nasty shock to realise just how shallow one was as a youth!

But do employers really care what people put on their Facebook profiles ? Well I dare say some do, but they probably should not. I’ve had more than my fair share of ‘youthful excesses’ in the distant past, but I’ve been a reasonably productive employee for all of that time. Now some more conservative companies may be worried about people making an association between their Facebook profile and the company they work for … fair enough. It seems perfectly reasonable to have a policy to say that one’s Facebook profile should not be linked to one’s place of work.

But not to employ someone because their Facebook profile looks a little wild ? That probably counts as cutting off one’s nose to spite your face! And quite possibly may count as age discrimination!

Now I come to identity theft. It is true that having too many personal details online may well make you more subject to identity theft which is a serious problem (although not a new one!). But is eliminating personal details online the right way of tackling the problem ? We have also seen this week that people can be subjected to the risk of identity theft through no fault of their own. Those who do not follow computer security news closely, may not realise that this is a story that is regularly repeated although not usually on such a scale.

Whilst being careful about putting personal details online is undoubtedly good practice (because no other solution is going to arrive quickly) we need to think about better ways of defending against identity theft other than hiding personal details. I have no ideal how this might be done in detail, although one obvious thing occurs … to have multiple ‘keys’ which serve different purposes … perhaps a government ‘key’, a financial ‘key’, a ‘social networking key’ (for things like Facebook and online forums), and a ‘key’ to be used for employer identity purposes. Seperating these ‘keys’ would limit the damage if a leak did occur … essentially you would need to steal multiple ‘keys’ to steal someone’s identity.

The problem of identity theft is only going to get worse unless we do something better in the future. Basing one’s identity on things like address, birth date, etc. is not going to be anywhere near like secure enough. It has always been possible to steal someone’s identity if you have these details, but the pervasiveness of IT systems makes it easier.

In the computer security world there is a truism that ‘security through obscurity is no security at all’, and what we are currently doing to protect our identity is attempting to practice security through obscurity.