Let’s apply for some of that sweet, sweet National Sanitation Foundation funding

Paul Alper pointed me to this news article about where the bacteria and fungi hang out on airplanes. This is a topic that doesn’t interest me at all, but then I noticed this, at the very end of the article:

Note: A previous version of this article cited the National Science Foundation rather than the National Sanitation Foundation. The post has been updated.

That’s just beautiful. We should definitely try to get a National Sanitation Foundation grant for Stan. I’m sure there are many trash-related applications for which we could make a real difference.

12 thoughts on “Let’s apply for some of that sweet, sweet National Sanitation Foundation funding

  1. Come to think of it, I’m sure the bio-statisticians amongst us can code a Generalized Regression On Correlated Haplotypes using an Orthogonal Spatially Censored Active Regime technique.

    Note: no brain cells were harmed in the making of this post, as they obviously weren’t used.

  2. Dear Garbage Man…

    “It is Stan’s first day on the job as a garbage man. He is very happy. The first piece of trash he finds in a horseshoe made of flowers, with a ribbon that says “Best Luck to Emily.” It is much too pretty to throw away, so Stan hangs it on the front of his truck. All day long people admire the cheerful-looking garbage truck named Emily. And the horseshoe is just the first thing Stan saves from Emily’s chewer-upper. At day’s end, Emily is piled sky-high with trash — Stan the garbage man doesn’t seem to want to put anything in the garbage! Recommended for ages 4 to 8.”

  3. While some may continue to chuckle over “NSF” referring to the National Sanitation Foundation, on occasion this blog has been known to focus on statistics. Here is how the Washington Post article put it:

    “Travelmath.com, a site that helps people calculate the driving and flying time between cities, ranked some of the dirtiest places in airports and airplanes, based on 26 samples gathered by a microbiologist sent to examine five airports and four flights.”

    The surprising results (median value for CFU = bacteria colony forming units) are

    1. Tray table – 2,155 CFU/sq. in.
    2. Drinking fountain buttons – 1,240 CFU/sq. in.
    3. Overhead air vent – 285 CFU/sq. in.
    4. Lavatory flush button – 265 CFU/sq. in.
    5. Seatbelt buckle – 230 CFU/sq. in.
    6. Bathroom stall locks – 70 CFU/sq. in.

    What is not surprising is that no notion of variability is to be found. That is, an average (median) is stated and the discussion ends. Moreover, the “26 samples” is ambiguous and it is impossible to tell from the Washington Post article or from the original

    http://www.travelmath.com/feature/airline-hygiene-exposed/

    what the 26 refers to. It may well be that one drinking fountain measurement was taken at 5 airports, one bathroom stall lock at 5 airports, one overhead air vent on 4 planes, etc., which adds up to 26 measurements. If this is so, we have another example of poor reporting of statistics. Even if 26 measurements were made for each of the above 6 places, that sample size is also suspect.

    • I would say even worse than the lack of precision estimates is the like of any context for the magnitude of those estimates. Like, OK, tray table = 2155, but what does that mean compared to, say, a public toilet at the park, or a surgery table? Or even better, the concentration at which Pr(sick | exposure) is above .01 or something.

      Yeah, precision is important, but only after the order of magnitude is known. This is why you get papers where the point estimate would suggest that, say, a 0.5sd increase in rainfall would end child malnutrition, or that the opening of a local health clinic would halve child mortality. Because the CI doesn’t include 0, and no one bothers to even check to see if it makes sense biologically. Or of course the opposite can happen too, that an input produces a very small but precisely estimated effect, and then people are like “you should really have your baby in October, because it will be smarter”.

Leave a Reply

Your email address will not be published. Required fields are marked *