No one told me that there’d linear algebra.

I mean, when I took MA 244, Clinton was President and few people outside of wonky Republicans, baseball fans, and Texans knew who the hell George W. Bush was. We all thought that Dick Cheney was done in Washington. Chads didn’t hang. This blog was still 15 months in the future.

Yet here I am in April 2014 trying to remember matrix notation for a Design of Experiments class. FUCKBEANS. I hate linear algebra.

Health Insurance

Thank you, fellow taxpayers, for the credit that defrayed about 80% of the cost of my health insurance.  Trust me, I’m ready to be back amongst your number, but while I’m playing the role of underemployed graduate student, it’s nice to be able to afford health insurance.  I’ve had some very mediocre insurance for the last couple of years through a student health insurance program, but that’s required me to maintain half-time status.  I would love to have the flexibility to drop back to a single class that I can focus on and work one or more part time jobs to cover expenses.  This allows me that flexibility.

I will save my complaints about the paucity of health coverage in Alabama for another day.  All I can tell you is that I had six or seven choices in dental coverage and just two in health — both from the same provider.  The silo structure of our insurance system — driven by the states — is another big problem.  If you really believe in marketplaces, you’d want more players in the game, right?  Instead, we have a system that favors consolidation.

[At least today's application process was smooth.  It's nice to see how easily the system moves when it's not full of people.]

Lent Has Brought New Life to the Old Blog

No, I’m not giving up Twitter after Lent is over, but needing a place to write some thoughts down has brought a bit of a rebirth to the old blog.  I was blogging before it was cool, and now I’m blogging after it stopped being cool.  While I don’t really know what all is going on with my friends, I’ve been trying to fight that with email.

When I look at the frustrations in that second link, I remember what they are, but only barely.  I only remember that they happened at all because I made vague references.  Letting the anger out is worth it, but I’m not sure that doing it where everyone can read it is the best thing.  I don’t know if the anger is any better-controlled, but not having a record of it may not be the worst thing ever.

My Tipping Jar Experiment, Round 2

So the first round of the tipping jar experiment went well.  There were two dominant factors: time of day and size of the jar.  I was not surprised that morning tipping was better than evening tipping, as the store is busier early than late.  I was surprised by the degree to which it dominated the results.  You use fractional factorial experiments to screen for results.  Normally, I would reduce this to a 23 experiment1 by dropping an insignificant factor; instead, I have changed how I collect my data and am re-running with the other three factors.  Instead of morning and night shifts allowing me to collect the data in 5-6 days, I’m using each full day as an experimental run, which will take me eight days.

I fully expect that tip jar size — larger was better, which surprised me — will continue to be a key player, but I want to know if opacity and seeding have main effects, and I want to know if any interactions occur.2  With a full factorial — even with a single replicate — I’ll be able to create a good reduced model once I see which main effects and interactions have any meaning.  It may be that tip jar size is the only factor that matters, but I won’t know until I take data.

I start in the morning and finish next Friday, which gives me 11 days to pull the data and plots together to write a paper.  It’s going to be a furious finish to the semester.  The big thing is that I now have to be there at least some of the time every single day for the next week-ish.  I’m there most every day, but now I have to make a concerted effort.

For future work, we’re going to refine the testing a bit.  Weekdays and weekends have different clienteles.  My tentative plan is to take data M-Th and F-Su, using those as blocks.  That really slows down my time to get results, but I won’t be on a schedule.  The baristas seem really interested in the results of this, which probably doesn’t surprise you.  They have ideas, too, and I’m the man that knows how to make the data happen.  It may take us all summer, but I bet we’ll be getting a good result at the end of it.  I’m already making plans!

  1. Three factors, each with two possible states. []
  2. E.g., how jar size and seeding interact []

Please Properly Possess Plurals

Morris is singular. The plural is Morrises. My house is Mr. Morris’s house. My parents’ house is the Morrises’ house. Plural nouns that possess things end in ‘, save for plurals that do not end in S, such as men, women, and children, which end their plural possessives with ‘s.

This was not the Charger’s worst hockey season, but it was the Chargers’. They won and lost as a team, and in America, teams are plural. (Step off, Britain.)

I just read a sports team’s alumni-run site, and they kept using “the Tiger’s season” repeatedly.1 Perhaps I am sensitive to this issue because my last name ends in S, but for fuck’s sake, people, this is not rocket surgery.

  1. Note: it’s not a team of tigers. []

Sun Kil Moon

I will always have April, and I am grateful for that. That record is so emotional and beautifully powerful that I am often moved by it. But damn if the next two albums are hard to love. I wish that I could adequately relay how few fucks I give about his past profligate promiscuity. I get it — you used to get laid a lot. Please evoke another emotion.

Tonight, I’ll dream of a girl with radiant, August eyes.

I Still Use (and Love and Recommend) Fastmail

It doesn’t matter that Microsoft has reconsidered its right to read your email if they’re doing things that they don’t like.  Seriously, that they did so quickly was great:

Effective immediately, if we receive information indicating that someone is using our services to traffic in stolen intellectual or physical property from Microsoft, we will not inspect a customer’s private content ourselves. Instead, we will refer the matter to law enforcement if further action is required.

This is a far cry from:

As part of the investigation, we undertook a limited review of this third party’s Microsoft operated accounts. While Microsoft’s terms of service make clear our permission for this type of review, this happens only in the most exceptional circumstances. We applied a rigorous process before reviewing such content. In this case, there was a thorough review by a legal team separate from the investigating team and strong evidence of a criminal act that met a standard comparable to that required to obtain a legal order to search other sites. In fact, as noted above, such a court order was issued in other aspects of the investigation.

They were well within their right to do as they did, but what they did was “wrong” in the moral sense of how the general public feels that they should handle things.  Going from a “we’ll police this” to a “let’s let law enforcement police this” position in a week or so is a great result from a huge company like Microsoft.  If this kind of agility is something that will be a characteristic going forward, I’m optimistic about their chances for relevance in 3-5 years.

But I’m writing today not to excoriate/praise Microsoft but to again champion Fastmail (note: referral link).  I fully stand behind my rant stating that I don’t trust Internet services that I don’t pay for.  Here’s why I use Fastmail.  Marco Arment uses Fastmail, and Michael Lopp is clearly thinking about it.  For something as important as email is, don’t use a provider that treats you as the product.  Your email is the product, and they have a responsibility to have as great of an uptime as possible.  You get what you pay for.  I’ve been using Fastmail for nearly eight years, and I’m very happy with it.

Geof F. Morris


There’s nothing like waking up at 0415 realizing that you structured your experiment incorrectly. Thankfully I’ve only taken 3/8 of my data. I’ll probably have to throw out one data point at the most.

ETA: Happiness is salvaging all of your data points, reworking the random order to tweak what you’ve run, and not losing any data taken already.  Hell, I’ll finish a day earlier.  Thank you, pagan DOE gods.

My Tip Jar Experiment

One of the two classes that I’m taking this semester is in design of experiments, which is more fun that it might sound.  I’ve done these before, and I think that the one that I’m doing now is pretty cool.

I ran an OFAT1 experiment back in middle school using paper airplanes and a contraption that ensured that they’d be propelled with the same force each time. Dad and I built a wooden box, entrapped a rubber band inside of a staple on the front of the box, and placed a clothespin at the back of the box that would hold the tail of the plane such that the nose of the plane a standard length from the front edge of the box.  Opening the clothespin launches the plane.  I ran five trials for each plane, averaged them, found the variance, and tabulated my standings.  I didn’t get first place,2 but I did have fun.

This experiment is more interesting and advanced.  I’m running a fractional factorial experiment, which means that I can test four factors in just eight runs without losing anything but higher-order interactions that aren’t likely to matter very much.  I’m using the coffeeshop that I spend a lot of time in, largely because I have the trust of the baristas that I’m not going to screw them over.  I have four factors:

  1. Time of day of the shift.  There are two shifts each day.
  2. The size of the tip jar.
  3. The opacity of the tip jar.  These two factors require that we have four tip jars.
  4. Whether the tip jar is seeded or not.

My premise is this: tipping baristas is a social phenomenon.  “Do I tip her?  All she did was make me a latté,” is a valid question.  Anything that we can do to shake up the social norm and show that, yes, people tip baristas is a good thing.  But I have no idea what factors will work.  That’s why you experiment, people.

I’m sitting here waiting on the end of the third shift under experiment.  #4 and #5 happen tomorrow, and the rest will conclude by Thursday.  I’m having fun, and so are the baristas, especially since I’m giving them money to participate.  I got some very interesting results yesterday, and I’m getting some predictable ones today.  Data!  I want more data!

I’ll get to do this one more time, either as a full 2^3 factorial that would test every factor combination, or by doing the alternate fraction of this 2^(4-1), which would test the other eight combinations.  I’d get to do the former if I have an obvious factor that has no value in the analysis of the first experimental run; if I don’t have conclusive data, I’ll do the latter.  I could also run another fractional factorial by dropping a factor and adding another one.

The ladies already want me to run more experiments.  I guess that I know what I’m going to be doing on my own time this summer.

  1. One Factor at A Time. In this case, it was the plane itself that changed. []
  2. Assholes! []