R starter resources

I’m hardly the first person you would want to talk to about learning statistics in R. But if you’re bent on teaching yourself R, and you’ve ended up at my blog, here are some resources I found useful. (No opinions here about whether R is good/bad better/worse than Excel, Minitab, Matlab, Octave, SPSS, Stata, SAS, or others.)

R Rroject is the mothership.

Rstudio is an IDE for R, which provides a better GUI for some basic tasks. Most of what you’d expect from a modern IDE: syntax highlighting, GUI commands for loading and saving data, setting the working directory, separate panes for help files.

UCLA tutorials are a well written introduction to basic data entry, functions, and graphics in R. There are similar tutorials for Stata and other languages here as well.

Quick-R is a blog and a book written by a statistician for people switching from SPSS and Stata to R. Excellent and concise website detailing all of the basics: data entry, functions, plots, and how to think about all of the above.

R help list and archives are a way to ask questions of experienced users. You’ll get excellent help here, but it’s important to respect the etiquette. Basically, (1) read the package manual, (2) work up a minimal example with your question, and (3) be extremely precise about the data you have and the data you want, as opposed to the way you’re trying to solve that problem. This will become clearer if you read a few discussions in the archives.

StackExchange is a glorified bulletin board for programmers exchanging help and (frequently great) advice. Search the archives before posting new questions–the guys that hang out here hate duplicate postings. But it’s easier to navigate than the R help archives.

Tufts Democrats: What did you think?

The Tufts Democrats got an earful from me about how US foreign policy on cyberspace hasn’t advanced significantly in fifteen years. I complained that a whole lot of basic questions haven’t been settled, and drew on some key national documents to verify that is the case.

They were more impressed with my rapid-fire interactive summaries of Hollywood takes on cyberwar and cyber dystopia. Or so they tweeted.

Jumbos: what did you think? Please post in the comments. Thanks!

Whither Cyberspace?

I gave a talk this morning about cyberspace at the Fletcher Doctoral Conference 2011. It was a panel with renowned expert Greg Rattray (FF’98), Professor William Martel, and Col. Tom McCarthy (FF’12+).

On one level, the topic was whether cyberspace is a domain and why. In another sense, it was a talk about why we’re still talking about that. With so much ink spilled since the 1990s on strategy of cyberwar, cyberattack, and cyber defense, why are we still dithering over first principles? And is there any practical effect? Is the domain determination consequential, specifically with regard to the organs of government and military to protect American interests.

Many of the hot current issues got raised during the Q&A:

1. How do we prepare government and the military to share responsibility for cyberspace with the private sector?
2. How do we characterize the risks of cyber attacks, and can we have any useful measures of them?
3. What is the government empowered to do on our behalf?
4. What makes attribution difficult, or even different, in cyberspace?
5. Why not simply refer nonstate cyber attacks to the relevant authorities in the host country?

Open Letter to Social Science Research Network

Dear SSRN:

If any of my works exist on your server, and if you intend to exploit them commercially, I wish to negotiate for a share of the revenues. I hereby opt out of any commercial exploitation of my works, either for a fee or as a free addendum to another commercial service, subject to further negotiation.

You may use works I have uploaded to your site prior to today under a CC-BY-NC-SA Creative Commons license. Details are available here. http://creativecommons.org/licenses/by-nc-sa/3.0/

Sincerely,

Ben Mazzotta

Cyber Shield newest mixed metaphor

This is the latest example of what’s wrong the metaphor of cyberspace for information security. Cyberspace isn’t a space. Cyber attacks don’t involve thrown projectiles or spears. A shield won’t bat them down. The meat of the policy is buried: look how little attention is devoted to the five points in the last paragraph quoted below.

If he had said that installing Norton Internet Security on every computer in America was the definition of a cyber shield, or ordering drone attacks against suspected zero-day-threat writers, or requiring American companies to write back doors for the feds into encryption, or mandating the use of federally issued firmware in critical industries….well, then that would be the definition of a cyber shield. It’s a completely empty term.

US urges NATO to build ‘cyber shield’
(AFP) – Sep 15, 2010

BRUSSELS — NATO must build a “cyber shield” to protect the transatlantic alliance from any Internet threats to its military and economic infrastructures, a top US defence official said Wednesday.

Cyber security is a “critical element” for the 28-nation alliance to embrace at its summit of leaders in Lisbon on November 19-20, US Deputy Defence Secretary William Lynn said in Brussels.

“The alliance has a crucial role to play in extending a blanket of security over our networks,” Lynn said.

“NATO has a nuclear shield, it is building a stronger and stronger defence shield, it needs a cyber shield as well,” he said at a forum hosted by the Security & Defence Agenda think-tank.

Demonstration of {estout}

I wrote a short talk demonstrating the use the R package {estout} for tonight’s New England R Users Group meeting.  NB this is not a discussion of the econometric model, but rather a demonstration of how to get publication-quality results out of R efficiently.

The basic functions of {estout} are modeled on the Stata package estout. Once the R user has a dataset and a regression format in memory, {estout} will

1. Print tables of summary statistics in CSV or LaTeX format.
2. Print regression results in CSV or LaTeX format.

All the normal bells and whistles for econometrics are in there: reporting both coefficient estimates and their standard errors, asterisks for alpha=0.10, 0.05, and 0.01 significance levels, R-squared and number of observations. Options to customize are clearly marked in the documentation.

Give new statecraft a chance

Mary Joyce, you lost me at hello. I can only hope you’re playing at fashion police, when you say “white guys in white shirts” are the status quo and therefore can’t represent change at the State Department. But we could try sending Ross and Cohen some hipster T-shirts to see if that helps.

The beliefs including ending the era of “white guys with white shirts… determining the relationship”, replacing ideology with openness, and broadcast with conversation.  Yet the policies described in the article reveal a shift in the type of “white men in white shirts” making policy decisions: away from career diplomats and towards young staffers and technology entrepreneurs. The article opens with a full-page photo (left) of the two young leaders of this movement – Jared Cohen and Alec Ross- walking in front of the Lincoln Memorial, Blackberries in hand: two white men in white shirts shaping the (new, digital) relationship America will have with the world.

R goes to StackExchange

“What’s the big deal? We already have the r-help mailing list.”

No, it’s a big deal. Really.

Have you forgotten the joys of being a first-year R user, either begging advice off of friends or using Google to search archives of the R-help list? (Firefox has a dedicated search add-on for the R-help archives.) Yes, it gets the job done, but it’s kludge. If you’re a self-taught R programmer you know what I’m talking about.

StackExchange for Statistical Analysis will let experienced users answer statistics questions, presented in a legible format, and good answers are promoted to the top of the list. Questions can be tagged by subject matter and by package. Proper formatting for code swatches, and for discussion. It’s modeled on StackOverflow.

Iraq Virtual Science Library looks great!

Congratulations to the web designer of the Iraq Virtual Science Library! IVSL looks great. I was astonished to find the site greatly improved since I last castigated them for bad marketing, registration, and web layout. The site is clean, intuitive, and responsive, at least from my desk in Boston.

Imagine my surprise when I received an email today with updated login information. My first thought was, “What a precisely targeted phishing email. Why would anyone want to phish my IVSL credentials?” Next year: I’ll convince IVSL not to send out username/password combinations by email.

Best wishes to IVSL and to my colleagues at the University of Duhok.

Fuzzy Thinking on African Botnets

I call “bull.” African botnets are not WMD, and the solution to African botnets is not to prosecute the lucky few who have computers there. Franz-Stefan Gady is completely out of touch with the realities of IT in Africa. The last thing African governments need is shunt scarce resources into prosecuting cyber criminals, particularly within their own borders. Please do something more useful with whatever resources you have: support export industries, build infrastructure, build a call center or an export processing zone, make jobs, and provide education and health care.

Honestly. Beefed up law enforcement? Where does Gady think most infections in Africa originate? Why would he presume that the botnets are home-grown?

Governments should find ways to make legitimate software available at prices users can afford. That means not taxing software imports, encouraging the use of free and open source software, and ensuring broadband access. Yes, greater bandwidth, and not less bandwidth, is crucial to safer computing. Bandwidth will give end users access to security updates and current virus databases that are prohibitively difficult to download when connections are slow.