Drawing conclusions from proxy data during extraordinary events

Note to the reader: this post refers to traffic data published by an adult video website. I do not link to that site directly, but pages linked in this post link to said website. I try to keep the content of this post safe for work, but use your own judgement.

How do people alter their behavior when they think they’re minutes from death? We got a chance to see just over a week ago when officials in Hawaii made a mistake. A very big mistake. They accidentally sent out a warning that a ballistic missile was inbound. For 38 minutes, people in Hawaii thought they were about to die in a nuclear attack.

An adult website that rhymes with “Corn Bub” found that their traffic dropped off dramatically during the time between the initial alert and the announcement that it was a false alarm. They compared traffic from Hawaii on that Saturday with the preceding two Saturdays and found at one point it was 77% below normal. After the all clear, page views spiked to 48% above normal.

One blogger used this to conclude that “nobody [engages in self-gratification] while waiting to die in a nuclear fire.” I cannot accept that conclusion without more supporting evidence. Under normal circumstances, I’d buy traffic to a mainstream adult website as a proxy for self-gratification. Not everyone uses such material, and those who do don’t all use the same website, but it’s probably a relatively stable representation of patterns. But the imminent threat of a fiery death is a (thankfully) unusual event that could drastically alter behavior.

Popular culture is rife with jokes and “sure, that totally happened’ tales of sexual activity when death looms (e.g. a crashing airliner). It’s entirely reasonable to believe that people figured “well, if I’m going to die, I might as well take care of this first” and immediately got down to business. Given the time constraints and the general stress of the situation, I would not be surprised if they didn’t partake in online content as they normally would.

Now I’m not saying that people did or did not engage in self-gratification during that time. I am saying using a particular website’s traffic as a proxy for that behavior is questionable. Even if it is reliable in normal circumstances. This is a particularly awkward example, but it’s a good lesson. If you’re not directly measuring something, don’t assume your proxies are valid in unusual situations.

Fun with birthdays

Sometimes I get distracted by shiny trivia. Shortly before St. Patrick’s Day, I noticed that seven of my Facebook friends happened to celebrate their birth on that holiday. That seemed surprisingly high, so I went through and counted up the birthdays for all 459 of my Facebook friends who have their birthday listed. The results are interesting. I don’t know if they’re meaningful or not.

As you can see from the I-should-have-made-it-larger chart above, any given day is most likely to be the birthday of one of my Facebook friends. It is slightly less likely to be the birthday of none of my friends. That was the most surprising result: I would never have expected that 108 days a year are empty when there are 459 birthdays to go around.

St. Patrick’s Day is the most frequently-birthed day with seven, although June 4 has six. According to the New York Times, those are the 134th and 146th most common birthdays. The most common birthday for those born between 1973 and 1999 is September 16, yet none of my Facebook friends claim that day.

May and December are the most common months for my friends, both with 52 birthdays. January is the least common with 25, though February and November each have 26. February gets some credit for being the shortest month, but it is still among the three months with less than one birthday per day. January does claim the longest stretch of birthday-less days, with eight.

How about days of the month? The 31st has the highest average, due to the 5s contributed by March and May (interestingly, these are the only two days with 5 birthdays). In second place, is the 22nd, which has the highest total count at 24. The lowest is on the 20th, which only has 6 birthdays. Two days before and after are in the 20s, so it’s a notable dip.

The full spreadsheet is available in Google Drive if you want to make your own observations.

2013 severe weather watches

Greg Carbin, Warning Coordination Meteorologist at the Storm Prediction Center, recently updated his website to include maps of 2013 severe thunderstorm and tornado watches. I always like looking at these, because they highlight areas of increased and diminished severe weather threat. It’s important to not read too much into them though. As with hurricanes, it’s not always the frequency of events that makes a year memorable. 2013 was a below- or near-normal year for watches in the areas of Illinois and Indiana that were hit by a major tornado outbreak on November 17.

Tornado (left) and severe thunderstorm (right) watch count (top) and difference from 20 year average (bottom) by county. Maps are by the NOAA Storm Prediction Center and in the public domain.

Speaking of hurricanes, the quietness of the 2013 Atlantic hurricane season is evident in the below-average tornado watch count along the entire Gulf coast. Landfalling hurricanes are a major source of tornado watches for coastal states, so an anomaly in watches is often reflective of an anomaly in tropical activity. Preliminary tornado counts for 2013 are the lowest (detrended) on record. It’s not surprising, then, that the combined severe thunderstorm and tornado watch counts are generally below normal.

Severe weather watches (left) and departure from normal (right) by county. Maps are by the NOAA Storm Prediction Center and are in the public domain.

As you’d expect, Oklahoma and Kansas had the largest number of watches. What’s really interesting about the above map is the anomalously large number of watches in western South Dakota, western Montana, and Maine. Indeed, western South Dakota counties are comparable to Kansas in terms of raw watch count. Of course, that doesn’t mean the watches verified, but it’s an interesting note. Looking back through past years, the last 4 years have been anomalously high in western South Dakota. Is this an indication of a population increase, forecaster bias, or a change in severe weather climatology?

There’s a world of data out there

While working on yesterday’s Weather Watch post, I decided that it was important to know what the normal river levels were this time of year.  After all, knowing the river stage is pretty useless without context.  Flood stage is pretty easy to find for most sites, but that doesn’t necessarily provide context for low-water situations.  For example, the Ohio River at Louisville, KY (McAlpine Lock and Dam, lower) has a flood stage of 55 feet, so being 15 feet below flood stage is normal.  In contrast, 15 feet below flood stage for the Wabash River at Lafayette, IN is four feet below ground.  The concept of pool stage exists, but it’s not widely used.  So how can river depth be put in the proper context for low-water situations?

Like most other data meteorological, a comparison to the average value over some period of time is apt.  The question then becomes “where do I find the average river height for a particular site?”  Of course, the average height can vary greatly over the course of a year based on local and upstream precipitation patterns, so month-by-month data is preferable.  Unlike temperature and precipitation, though, the National Weather Service does not issue daily climate summaries for rivers (at least not that I’ve seen).

Fortunately for the numerically-minded, the United States Geological Survey (USGS) has a wealth of data available for free on the Internet.  It’s a little tricky to navigate, but with patience, the National Water Information System (NWIS) will surrender the desired information.   With data for approximately 1.5 sites available in a variety of readable and parseable formats, there’s enough to keep even the most efficient data nerd busy for a long time.  For easier-to-navigate real-time hydrologic data and forecasts, see http://water.weather.gov/ahps/.