If statistical packages were books

Which books would they be? Here's what I think:

1. SPSS: Dan Brown, The Da Vinci Code (hardcover edition)

Best summed up by a quote from Homer Simpson: "You take forever to say nothing!" There are people out there who actually think this is a great book. The rest of the world thinks those people are crazy and, while no one goes as far as to advocate isolating them, no one lets them babysit their children either. To make up for its fatal flaws in narrative, historical plausibility, character development, and a laughable plot, the book is also very expensive.

2. Microsoft Excel: J.R.R. Tolkien, The Hobbit

This is a book everyone has read and enjoyed, though no one is bragging about it. Despite being so low-brow, however, this is actually a very decent book. As long, of course, as you take it for what it is; some read it as though it were The Lord of the Rings, which can lead to bitter disappointment.

3. Stata: Terry Pratchett, Discworld

It's a niche book that all of its readers for some reason think is mainstream. It's an incredibly fast and entertaining read, but don't let that fool you: it's full of profound insights and reading it can be an unexpectedly powerful experience.

4. SAS: The Bible

Everyone has a copy, but no one remembers how they got it. It's everyone's answer to "What's the greatest book of all time?", but no one is sure why. It's an incredibly hard book to read, but common wisdom claims that if you understand it, you can find in it things that no other book can offer. Those who do understand it and have found these things, however, seem to be unable to effectively communicate their experience; and if you ask them to, they'll usually tell you to go back and read the book yourself. It's written in style that requires four paragraphs to say "Hello." Nothing is what it seems and no one does anything expected. Every once in a while, however, it will offer a passage that will answer one of your deep questions or solve one of your deep problems. And then, as soon as you try to tell someone about what happened, you'll find that they just can't understand.

5. R: Leo Tolstoy, War and Peace

It's long. It's one of the longest books ever. Takes forever to read. It's so damn long that many times you'll be convinced there's no way you can finish it. In addition, Tolstoy fans (as opposed to Pratchett fans) can be quite an annoying and pretentious crowd. Everyone would like their friends to think they've actually read War an Peace. But hey, don't blame Tolstoy for it: the book is great. Sure, it could be simpler and shorter. But it has a lot to offer. It can make you think differently about what you thought you already knew. It can make you notice that things you previously took for solutions to problems are actually nothing more than one-time acts of desperation. And every once in a while, it can even entertain you.

The ideal solution would be to starve

Here are brief excerpts of an interview with Mark Meckler, leader of the largest Tea Party group.

Is there any scenario where you think it would be OK to raise the debt ceiling?

No.

What do you think is the ideal solution to this impasse right now?

The ideal solution is to cut spending so that we stop spending beyond our means.

Now the 2011 federal budget is $3.7 trillion, of which about $1.5 trillion has to be borrowed. Correct me if I'm wrong, but it seems to me that Mark Meckler thinks that we should cut federal spending by 40%, this year. Why would anyone take this guy seriously?

Innumeracy, big time

A New York City-based organization called the Coalition for the Homeless is currently running a TV public service announcement in which they say:

Which is more disturbing: That each night in New York City, more than 40,000 people are homeless, or that the average age of a homeless person is 9?

(Or something to that effect. I'm paraphrasing, but the figures are quoted accurately.)

If the avarage age of 9 strikes you as implausible, you're right. The very same Coalition for the Homeless lists the following as one of the basic facts about homelessness:

In New York City... Each night more than 40,000 people--including more than 16,000 children--experience homelessness.

This basic fact makes the average age of 9 an arithmetic impossibility. 16,000 is 40% of 40,000; so even if each age category (children and adults) is assumed to have the lowest average age possible (1 and 18, respectively), the average age of a homeless person would be 11. But of course these assumptions are empirically completely implausible, which means that the average age of a homeless person is not only certainly greater than 9, but most likely much more so. Assuming group averages of 3 and 30, for example, gives an overall average of 19. The only nationwide data that I have been able to find is here, from which the average turns out to be about 32 (see Exhibit 5-3 on page 43).

How's that for innumeracy?

If you can watch this without crying, something is wrong with you

The handshake is definitely secret

The way in which the name LaTeX is pronounced often serves as a secret handshake: If you've never used LaTeX but your resume says you did, you'll most likely give yourself away during a job interview by pronouncing the name incorrectly. Is this intentional?

The 'genetic or voluntary' false dichotomy

It's a very irritating one because it is so glaringly false. Example: in arguments concerning homosexuality, it's often assumed that if this orientation is not genetic, it must mean that it's a "lifestyle choice."

My native tongue is Polish. That's the way I am; I had precisely zero choice in this matter. Are you really telling me that this implies there must be a gene regulating things like that? I assure you there isn't. You can sequence my genome till kingdom come and you will never find a 'Native Tongue' gene with a value set to 'Polish' anywhere in there.

Stunning links

Surely this can't be right.

Surely this can't be right either.

A short guide on how to get everything you can possibly get wrong, wrong.

Is the latest minimum wage increase binding?

Denying does not mean refuting.

Something we all need to remind ourselves every once in a while: Most published research findings are wrong.

Hypocrisy anyone?

I've recently heard one of the leaders of Polish opposition assure voters that if his party wins the elections, they'll change the law so that in the time of a severe economic crisis, the government will be required to create a certain amount of public sector positions and recruit the unemployed to fill them. Those positions, the politician said, should be targeted especially towards recent college graduates in search of their first job.

So let me get a few things straight here. Public education in Poland (including college education) is funded entirely by the state. Politicians (also those from the very same party) defend this status quo fiercely, and one of their main arguments is that investing in human capital makes sense because it reduces unemployment. In other words, they're saying that the state should fund students' college education, because if it doesn't, they'll have trouble finding jobs. And also that if an education that was state-funded because it helps find jobs, doesn't help find jobs, then the state should fund jobs.

Why don't we skip the education silliness altogether and just give everyone a public sector job when they turn eighteen?

Is ignorance the worst evil?

If we care about the common good, then reason will clearly tell us what moral code to follow: it will tell us to follow the rule utilitarian moral code. But if we have no concern for the common good, then reason cannot tell us to follow this moral code (or any other).

Those are the concluding words of a paper in which John C. Harsanyi, one of the greatest economists and philosophers ever, summarized his groundbreaking game-theoretic research in moral philosophy. It probably was not his intention, but those words I think sum up the reason why all of the moral codes we have ever evolved are essentially irrational. A rational code of ethics, whether utilitarian or some other type, is a luxury that we as species simply could not afford, because reason can guide moral choices only in situations when everyone involved "cares about the common good". For beings who all want to be good but cannot reach a consensus as to exactly what kind of actions make good things happen, rule utilitarianism is indeed the answer. In this type of world, the worst evil is caused by lack of knowledge as to how various possible rules constraining individual behavior affect that behavior in the long run. Religious dogmas are a good example of such ignorance, as are almost all other moral systems of the deontic variety (i.e. those positing that following moral rules is a value for its own sake). In Harsanyi's world, moral rules evolve not because people think they are an unqualified good, but because too much utilitarianism can be a bad thing. If I gain more utility out of using your car than you lose because of my stealing your car, then simple-minded utilitarianism says it's OK for me to steal your car. This leads to less utility in the long run than we'd have in a world where it's not OK to steal a car from someone just because you think you'd enjoy it more than the owner. Hence we should have a moral rule saying it's not OK to steal.

Such concerns, however, are not the main reason why moral rules evolved in our world. In our world, the worst evil is the result not of ignorance but of deceitful malice. In our world, there are those who not only have no concern for the common good, but who actively seek to hurt others while pretending to be good. Harsanyi's world is a coordination game, or at worst a stag hunt, whereas the real world is a prisoner's dilemma. In a repeated prisoner's dilemma, bright line rules are the only way for a society of cooperators to protect itself from cheaters, even though bright line rules have dire side effects such as unforgiving dogmatism and lynch mob mentality. In our situation, those consequences are a price worth paying. Our ethics are indeed irrational; but it's not because we lack insight, but because the worst enemies of our society are not "moral imbeciles" but moral predators.

Here's something one doesn't see very often

A conflict between country's central bank and its department of health. Latvian central bank has recently released a silver 1 Lat coin featuring a beer mug on reverse, which motivated Latvian health department officials to accuse their central bank of "covert advertisement of alcohol." If that's the sort of problems they have in Latvia, I want to move there.

Education in Poland is not underfunded, take 2

This is a footnote to a previous post arguing that education in Poland is not underfunded, with the graphical part of the argument made more persuasive by the use of a great R package called rworldmap:

How much bang for the buck this spending offers, however, is a different question: