Crooked Timber’s Greatest Hits

by Kieran Healy on June 21, 2004

In the course of the recent “great database fiasco”:, I took a look at the history of traffic to this site. The AWStats program gave me a the number of unique visitors for every day from our launch last July through to June 16th this year. I was interested in which posts had made the biggest splashes. Now, if I just looked at the posts that got the greatest number of visitors, there would be a bias towards posts from later in the year, because we get far more visitors these days than six or ten months ago. How can we get a fair estimate?

It’s possible to statistically “decompose”: a time series into three components. First, there’s the _seasonal_ component: in this case, it’s the regular ups and downs caused by what day of the week it is. Generally, traffic will dip every weekend, regardless of how many visitors we’re getting on average. The average number of visitors from week to week net of the seasonal ups and downs is the second, _trend_ component. This has grown consistently over the year. And finally there’s the _remainder_ or “irregular” component, which is whatever spikes and dips are left over once seasonal fluctuations and the underlying trend are accounted for.

The nice picture above shows CT’s unique daily visitor series decomposed in this way, with the raw data at the top and the three components underneath. (You can also get this figure as a “higher quality PDF file”: [only 34k].) As you can see, the trend is one of healthy growth. These days we typically get about seven to nine thousand unique visitors a day. But what about those spikes in the lowest panel? Which posts brought in the crowds? *Read on* for the Top 10 list. The punchline is that, even though we’re known for being a bunch of “pointy-headed academics”:, the out-of-the-ballpark hitters on our roster are not the ones with Ph.Ds.

Before counting down through the list, I should make an *Honorable Mention* of two posts that are just outside the top 10 and have nothing to choose between them in terms of impact. “Stories”:, by Ted, took on the controversy about MeCHA and Cruz Bustamente (remember him?). And “Bats Aren’t Bugs”:, by John Holbo, showed that despite his self-conception as an empirically-driven pragmatist, “Steven Den Beste”: is in fact the Hegel of the blogosphere.

*Crooked Timber’s Greatest Hits*

*10*. “Grrr”:, by Ted. Ted reproduces an essay about the meaning of the September 11th attacks that itself might have a further CT connection.

*9*. “DC 5/11: Day of Inconvenience”:, by Ted. Speculating about what the President’s testimony (“I only plan to talk for an hour, that’s all you’re getting”) before the September 11th commission would be like.

*8*. “Books I Did Not Read This Year”:, by Kieran. A Top 10 list makes the Top 10 list. Probably got in because it got a relatively large number of hits during the relatively quiet week before Christmas.

*7*. “Left-Wing Conspirators”:, by Kieran. The bizarre bedfellows in David Horowitz’s database of Left Wingers.

*6*. “Air MILES!!!!”:, by Daniel. Dsquared satisfies all your Friedman BS-detection and debunking needs. One day Daniel really is going to run into Tom in a frequent flyer lounge somewhere. I hope they are both drunk when it happens.

*5*. “Bright is as Bright Does”:, by Kieran. Brights are the MENSA dweebs of the new century. This makes the list because it was the first CT post to get a lot of coverage after we launched.

*4*. “Why I don’t like Mickey Kaus”:, by Ted. Why Ted doesn’t like Mickey Kaus. It’s a good reason, too.

*3*. “All Gone to Look for America”:, by Daniel. “There used to be a shining city on a hill … what the hell happened to it?” Indeed. As someone might say.

*2*. “Punk the National Review”:, by Ted. The NRO’s practice of publishing anonymous letters is killed. Dead. By Ted. You thought it was impossible to force Jonah Goldberg to raise his standards, but all that’s really impossible is getting him to admit that you did.

*1*. “Tomorrow’s Kerry-bashing Today”:, by Ted. Looking into future misdirection and smears about the Kerry campaign. Coming soon to pundits everywhere, seen here first.

So the pattern is pretty clear: On this measure, Ted and Dsquared bring in the punters. Daniel mobilizes the foreign policy crowd and Ted has a terrific knack of capturing the left _zeitgeist_ in U.S. politics. If I were a Democratic party strategist I would consider hiring Ted. (As a consultant only, please: we want to keep him.)

Of course, the method I used isn’t the only way to make a list like this. Some posts are slow burners, attracting sustained attention over a longer time period. If we look at the number of visitors posts get once they are up, the posts in the top-10 list still dominate but some of the slow-burners also come to the fore. These include:

* “ETA/Al Qaeda: Who did it?”: by Maria.

* “Singer vs Bush”: by Brian.

* “Gambling with the Devil”: by Chris.

* “Conservatives in Academia”: by Kieran.

* “Susan Moller Okin”: by Harry.

* “Some Unsolicited Advice for John Kerry”: by John Quiggin.

I still like the time-series decomposition, though, in part because I get to produce a nice graph but mostly because it gives me an extra reason to like CT: Crooked Timber has a bunch of literate academics from all over the world who do high-quality research in the social sciences and humanities and who write lots of interesting stuff — but the great thing is, they aren’t even our most popular draws.



Kevin 06.21.04 at 11:08 am

Is my computer kaput or is that graph sitting on top of the text? And if Daniel isn’t a literate academic etc., what is he apart from being “a fat young man without a good word for anybody”?


jholbo 06.21.04 at 12:54 pm

I want a special category for most influential post measured by largest number of redundant, duplicate track-backs. This would show which posts caused people who linked to the post to think TWICE, three or even four times, editing their posts accordingly. I believe I quietly excel in this category. Take a look at my ‘academic lit blogging’ post, for example. Thanks for fixing all the stuff, Kieran. Very heroic of you. And for compiling the fun greatest hits stats.


Factory 06.21.04 at 1:04 pm

Erm I’m no expert, but shouldn’t the remainder be scaled by the trend? (to eliminate the advantage that posts made during busy periods would have)


Claire 06.21.04 at 3:12 pm

Stating the obvious here, that’s a lot of visitors. Do you know how many are repeats?


Ted Barlow 06.21.04 at 3:45 pm

I thought Daniel had a PhD. in economics, but wasn’t an academic.

(And I’ll bet that John Holbo is right about his claim to fame.)

Huge thanks for all of this, Kieran.


Richard Bellamy 06.21.04 at 3:49 pm

I regularly log in every weekday from about 8900 unique computers. That leaves a couple dozen other readers, tops.

But I get renewed enjoyed and and enlightenment with each of those unique readings, so from a utilitarian point of view, you shouldn’t really care that I’m one of your only readers.


Richard Bellamy 06.21.04 at 3:49 pm

I regularly log in every weekday from about 8900 unique computers. That leaves a couple dozen other readers, tops.

But I get renewed enjoyed and and enlightenment with each of those unique readings, so from a utilitarian point of view, you shouldn’t really care that I’m one of your only readers.


Nabakov 06.21.04 at 6:15 pm

I vsisited once. Are you sure you counted it? I have the documenation.


fyreflye 06.21.04 at 10:13 pm

I’ve never visited and have no intention of doing so. Please remove me from your chart if I’m on it.


Chris Marcil 06.21.04 at 10:58 pm

When are the Neptunes going to remix some of these hits?


Backword Dave 06.21.04 at 11:37 pm

Maria once sent me a book (still not finished, but found after declared lost) after I was the first person to comment on a post. If I’d have known you were going to play an evil game like this, I’d have loaded that page every minute for days, and bandwidth be damned!


Glen 06.22.04 at 2:34 am

I couldn’t read the whole post because the graphs were sitting on top of the text. But here’s my question: given that there are multiple posts on most days, how did you know which posts to attribute the visitors to?


Kieran Healy 06.22.04 at 4:20 am

how did you know which posts to attribute the visitors to?

We know which posts get lots of hits (and what day they were posted) and we know which days gets lots of hits (and what posts were up on that day). Although it’s certainly possible, it turns out that in practice there’s basically never any ambigiuity about which posts get the credit, as it doesn’t seem to happen that two posts get a big wave of attention at once — this seems to be a consequence of people’s habits when it comes to linking to other blogs.


Adam Kotsko 06.23.04 at 12:53 am

Re: “jholbo” — Does anyone know what causes the redundant trackback thing? Is it really that the person just edits their post?

Personally, I never have that problem, because I’m fortunate enough to use HaloScan’s super-advanced trackback, which never sends a trackback ping unless you explicitly go through a 14-step process with three separate browser windows open.

Comments on this entry are closed.