Analysis of the statistics blogosphere

My analysis of the statistics blogosphere for the Coursera Social Networking Analysis class is up. The Python code and the data are up at my github repository. Enjoy!

Included are most of the Python code I used to obtain blog content, some of my attempts to automate the building of the network (I ended up using a manual process in the end), and my analysis. I also included the data. (You can probably see some of your own content.)

Here's what I learned/got reminded of the most:

• Doing projects like this is hard when you have other responsibilities, and you usually end up paring down your ambitions toward the end
• Data collection and curation was, as usual, the most difficult process
• Network analysis is fun, but I have a ways to go to know where to start first, what questions to ask, and so forth (these are the things you learn with experience)
• The measures that seem to be the most revealing are not always obvious -- in this network, it was the number of shortest paths compared to a random graph
• Andrew Gelman's blog is central (but you probably don't need a formal analysis to tell you that)
• There's a lot of great content about statistics, data analysis, data science, and statistical computing out there. I've relied on blog posts for a lot of my work, and I've found even more great stuff. It's a firehose of information.

List of statistics blogs

Here is a list of 40 statistics blogs. I read many of them regularly, but there are a few that are new to me.

PMean - STaTS reborn?

I have referred to the STaTS pages in the past for statistical references. Sadly, Children Mercy hospital has temporarily taken down the pages, but Steve Simon has resurrected some of his content (and hopes to be able to get all of his content back) and more at pmean.

More stats sites

Jim Albert has a blog based on his book Bayesian Computation in R. Unfortunately, it seems they haven't been updating it too much recently but it looks like what's there is pretty good.

Forums!

Cool. Flowing Data now has forums!

Well, why not?

Since I'm posting, I might as well point toward Derek Lowe's post about the failure of the Singulair/Claritin idea. Too bad for Merck, though one has to wonder how long this drug combination strategy among big pharma is going to play out. After all, wouldn't it be about as cheap to take two pills (since one is over-the-counter) as it would be to ask your insurance to fork it over for a prescription version of a combination? Heck, a lot of people take the combination separately now, anyway.

So at any rate, Derek deduces that the problem lies in efficacy. Is it possible to support a marketing claim that the combination is more than the sum of its parts? Merck apparently thinks so, but the FDA does not. Unless there's an advisory committee meeting on this, or the drug eventually gets approved, or efforts to get results of all clinical trials posted publically succeed, we won't know for sure. But what I do know is that for one of these combinations to gain marketing approval, at the very least there has to be a statistically significant synergistic effect. That means that the treatment effect has to be greater than the sum of the treatment effects of the drugs alone. Studies that demonstrate this effect tend to have a lot of patients, especially if there are multiple dose levels involved. It isn't easy, and I've known more than one combination development program to fizzle out.

Update: but see this serious safety concern for Singulair reported by Pharmalot.

Notable addition to the blogroll

I just found a new biostatistics blog called Epidemiological Methods. The posts I've looked at so far are high quality, and the blogroll is high quality as well.

Oh, and via that, I found a Bayesian Stats blog, too.