Category Archives: Academia
I just found this sitting in my drafts folder. It’s from May:
The question they seem to keep coming back to is: “What’s in the data?” Statistics seems to be everywhere…
I was recently reading Gelman’s blog, and he wrote a post about this: Patents Aren’t Only for Engineers. Apparently, some actuary received a patent for statistical sampling. The author (is that what they are called?) of the patent, Jay Vadiveloo, is a mathematics professor in residence at the University of Connecticut, and he is quoted in the article as saying:
To me, the results were astounding: statistical sampling worked.
At this point, I thought I got the joke and I went to check the date that the article was published expecting to see April 1. Nope. May 12 actually. So, this is serious? If this is serious, this is — how can I say this nicely — astonishingly…..I have nothing nice to say here. So I will say nothing. Congratulations, professor Vadiveloo.
Gelman goes on to write:
P.S. Mendelssohn writes: “Yes, I felt it was a heartwarming story also. Perhaps we can get a patent for regression.”
I say, forget a patent for regression. I want a patent for the sample mean. That’s where the real money is. You can’t charge a lot for each use, but consider the volume!
This reminded of a conversation I had with a fellow graduate student in statistics who had done an internship at an insurance company over the course of a summer. They explained to me that someone in the insurance industry had either tried to patent or already had a patent for multiple regression for use in insurance. Now, I wasn’t sure how true the story was when I heard it, and I’m still not sure how true the story is, but if you can get a patent on sampling, I suppose anything is possible.
Question for a lawyer: If someone can get a patent on sampling after it has been around in the statistics literature for a very, very long time, can I just go through more recent statistics literature and just start filing patents on other people’s ideas?
I’m not actually going to do that, but that is a serious question. What is preventing me from doing that?
Is it possible that your writing style is identifiably unique? In the late 1800s, a Polish philosopher named Wincenty Lutosławski imagined a “future science of stylometry,” whereby the singular style of an author could be quite literally measured. In such a future, controversies over authorship would be resolved not by literary scholars but by statisticians, and data would provide the answer. Sounds like pie in the sky, right? But it turns out that Lutosławski was right. Over the past 50 years, stylometrists have fashioned a promising way to identify authorial signatures using something called “lexical glue.” Listen as Bob Garfield and I talk about how a bunch of seemingly inconspicuous words actually stand out.
It’s almost as if statistics is everywhere. Oh wait. It is…
When I did my Master’s degree at WPI, Erik was a second year student who went on to do a Ph.D. at, I believe, the University of New Mexico. He helped me tremendously in my first year in graduate school and always seemed to have good advice (as well as “fake” good advice usually telling us to “always sum the residuals”). I haven’t seen Erik in years, but I follow his blog. His latest post links to his “Teaching Dossier“, which catalogs his teaching experience. (Apparently he was awarded “2011-12 UNM Math & Stat Outstanding Undergraduate Instructor.” Congratulations!) While that probably isn’t of interest to most people, the first 17 pages or so is his “Reflective Statement on Teaching Philosophy, Practices, and Goals”, which I found to be very interesting.
I hate impact factor….