Simply Statistics

31
Jul
31
Jul

If I were at #JSM2012 today, here's where I'd go.

Obviously, there are tons of sessions everyday at JSM this week and it’s physically impossible to go to everything that looks interesting. Alas, I am but one man, so choices had to be made. Here’s what looks good to me from the JSM program:

  • 8:30-10:20am: Contemporary Software Design Strategies for Statistical Methodologists, HQ-Sapphire B
  • 10:30am-12:20pm: Stat-Us Update from Facebook, HQ-Sapphire EF
  • 2:00-3:50pm: Astrostatistics, CC-Room 29A or Results from the 2010 Census Experimental Program, CC-Room 30A (perhaps you can run back and forth?)

Lots of other good stuff out there, of course. I wouldn’t mind hearing some feedback on how these go.

30
Jul

Why I'm Staying in Academia

Recently, I’ve seen a few blog posts/articles about professors leaving academia for industry or some other non-academic position. By my last count I think I’ve seen three from computer science professors leaving academia for Google. The most recent one being from Terran Lane at University of New Mexico. At this point, Google should just start a recruiting office in middle of all the CS departments around the country. I think they’d get some good people.

Each of the “fairwell” blog posts cover many of the same points—difficulty with having an impact, increasing specialization of academic research, difficult funding climate, increasing workloads—and, frankly, all of this is true to varying degrees. Beki Grinter has already written a pretty good response. One topic, massive open online courses (MOOCs), is something on which I’ll comment at a later date. For now, I thought I would add a few of my thoughts.

  • There’s no perfect job. Many of the problems affecting academia—difficult funding, increased workloads—are affecting other industries too. Right now we’re in the worst economic recession in decades and money is tight everywhere. I find it difficult to imagine that there’s a job out there that doesn’t suffer from some form of economic or other constraint. Academia needs to find some solutions, for sure, but times are tough everywhere unfortunately.
  • This is about as close as it gets to the perfect job. Really, it’s a pretty good gig. Everyday I come into work and I sit down and work on whatever I want. I’m surrounded by fantastic students and postdocs and when I walk the halls I can talk to great people who are smarter than I (even if they don’t necessarily appreciate me barging in). But that said, it’s not an easy job. The reality is that every professor is a like 1-person startup company, and you need to work pretty hard to stay afloat. (Okay, I’ve never worked at a startup, but I imagine they work pretty hard there.) They don’t tell you that in grad school but, then again, there’s a lot they don’t tell you in grad school.
  • It helps to work at a medical institution where tenure is meaningless. Okay, I’m being a bit facetious here…but not really. Much of academic anxiety comes from the need to “get tenure”. At most medical institutions, while tenure exists, having it is fairly meaningless (getting it, of course, is still very tough). The reason is because most medical researchers are funded on soft money, so somewhere between 60% to 100% of their salary is paid from grants. Whether this is a good way or a terrible way to do things is worth discussing at a later date, but the end result is if you can’t fund your salary, getting tenure isn’t going to magically come up with the missing dollars. Universities can’t afford it using the current model. So while tenure is a tremendous privilege and honor and will secure your position at the University, it can’t secure your salary. In the end, what I really need to be focusing on is doing the best research. There’s really no “game” to play here.
  • The best way to have an impact is to do it. Every University is different, for sure, and some put many more constraints on their professors than others. I consider myself lucky to be working at an institution that has substantial resources and is in relatively good financial condition. So in the end, if I want to have an impact on statistics or science, I just need to decide to do it. If one day someone comes to me and says “stop what you’re doing, you need to be doing something else”, then I might need to reconsider things. But until that day comes, I’m staying put. It might turn out I’m not good enough to have an impact, but we can’t all be above average.

Ultimately, I don’t want the many grad students out there who may be considering a career in academia to feel discouraged by what they might be reading on the Internets these days. There’s good and bad with every job, but I think with academia the balance is fairly positive, and you get to hang out with cool people

Of course, if you’re in computer science, you should just go to Google like everyone else.

29
Jul

Statistician (@cocteau) to show journalists how it's done

Mark Hansen, a Professor at UCLA’s Departments of Statistics and Media Arts, has been appointed as the inaugural Director of the David and Helen Gurley Brown Institute for Media Innovation. The Institute is a joint venture between Columbia University’s Graduate School of Journalism and Stanford’s School of Engineering.

The Institute and the collaboration between the two schools is groundbreaking in that it is designed to encourage and support new endeavors with the potential to inform and entertain in transformative ways. It will recognize the increasingly important connection between journalism and technology, bringing the best from the East and West Coasts.

Congratulations to Mark for this fantastic opportunity!

29
Jul
28
Jul

Tweet up #JSM2012

If only because I won’t be there this year and I need to know what’s going on! Where’s the action?

28
Jul
28
Jul
27
Jul
27
Jul

How important is abstract thinking for graduate students in statistics?

A recent lunchtime discussion here at Hopkins brought up the somewhat-controversial topic of abstract thinking in our graduate program. We, like a lot of other biostatistics/statistics programs, require our students to take measure theoretic probability as part of the curriculum. The discussion started as a conversation about whether we should require measure theoretic probability for our students. It evolved into a discussion of the value of abstract thinking (and whether measure theoretic probability was a good tool to measure abstract thinking).

Brian Caffo and I decided an interesting idea would be a point-counterpoint with the prompt, “How important is abstract thinking for the education of statistics graduate students?” Next week Brian and I will provide a point-counterpoint response based on our discussion.

In the meantime we’d love to hear your opinions!