2014 NHL season results

In February, I predicted the results of the 2014 NHL regular season based on the results of the Men’s Olympic hockey rankings. Now that the season is over, the projections can be compared to the results:

Team
Actual rank
Predicted rank
Boston113
Anaheim25
Colorado314
St. Louis42
San Jose511
Pittsburgh66
Chicago73
Tampa Bay811
Montreal98
Los Angeles109
Minnesota1115
NY Rangers127
Philadelphia1320
Columbus1420
Detroit151
Dallas1617
Washington1719
Phoenix1810
Nashville1925
New Jersey2027
Ottawa2125
Winnipeg2218
Toronto2323
Carolina2423
Vancouver254
NY Islanders2620
Calgary2730
Edmonton2827
Florida2927
Buffalo3015

A few of my predictions were well off (e.g., Vancouver, Buffalo, Detroit, Colorado, and Boston), but I still wanted to determine if my Olympics predictions were correlated to a statistically significant level with NHL season results.

The first step is to formulate my hypothesis (which I somewhat alluded to in my previous post). The null hypothesis—which I hope to reject—is that my Olympic predictions have no correlation to the NHL season results (they are independent). The alternative hypothesis is that there is a correlation.

The next step is to find an appropriate test statistic. Since these lists are both rankings (i.e., ordinal data), either Spearman’s rho (ρ) or Kendall’s Tau (τ) would be a good choice (they can be used to measure rank association, or the similarity of ordered rank data). I will use both for robustness. They should tell us if the two variables (predicted and actual) are statistically dependent. The null hypothesis, that the two are independent, would yield a value of zero for both measures. An ideal correlation would give a value of +1 (perfect positive correlation).

Here is perfect correlation:

Perfect correlation between actual and predicted results

Here are my results:

Olympics predictions versus NHL season results

At a glance, the correlation does not appear strong. But is it statistically significant?

Both Kendall’s Tau and Spearman’s rho reject the null hypothesis of independence at an alpha of 0.1%. Kendall’s Tau is 0.46 and Spearman’s rho is 0.64—both suggest a statistically significant correlation between the rank I predicted based on the success of players’ teams in the Olympics and the NHL season results.

If not for the five “outlier” teams I mentioned earlier, the results become extremely promising (Spearman’s rho > 0.86). However, manipulating the data after the fact is questionable without a good reason. What would be better is to find the reason why those five teams did so much better/worse than my Olympic prediction projected.


Posts in this series:

The inquiry-based learning bandwagon

In December, a petition was created in Alberta by Dr. Nhung Tran-Davies, which calls for a “Back to basics” approach to mathematics. It is nice to see parents analyzing the Alberta K-12 curriculum critically. The education of our children is very important, and not something we should accept if we are unhappy with it.

However, I question how many parents have actually looked at the curriculum. I doubt many have considered anything beyond anecdotal evidence. It’s one thing to read a story in a newspaper article or on a Facebook page; it’s a different story entirely to read it for yourself.

The story of the day—indeed, the focus of Dr. Tran-Davies’ petition—seems to be kids failing to learn multiplication tables. Here’s what the curriculum states as specific outcomes in grade 3:

Demonstrate an understanding of multiplication to 5 × 5 by:

  • representing and explaining multiplication using equal grouping and arrays
  • creating and solving problems in context that involve multiplication
  • modelling multiplication using concrete and visual representations, and recording the process symbolically
  • relating multiplication to repeated addition
  • relating multiplication to division.

These strategies sound awfully familiar to what I learned years ago in grade 3. But to those complaining, I ask: Where does it mention inquiry-based or discovery learning? Where does it suggest a student does not need to know how to do multiplication? I’m not asking what a biased politician or newspaper article claims. I’m asking you.

I’m unsure what it is Bruce McAllister (the Wildrose Education Critic, who has taken up this case in Alberta’s Legislative Assembly), Dr. Tran-Davies, and others are expecting in terms of teaching multiplication. Should we monotonously repeat the times tables after the teacher, ad nauseum, for hours on end like our grandparents did? That might work for some students, but not others. For those students that learn this way, great! But for others—those who would have been lost or considered “dumb” in my grandparents’ youth—this is no way to learn. Teachers are constantly learning and educating themselves on better and more complete methods of teaching; ways that let every student learn, not just a select few. The best teachers are the ones who make more than just one method of learning available to their students.

All the curriculum states is what students must learn, not how. The teachers who are doing what they can to engage the greatest number of students (those “accused” of inquiry-based learning—which, by the way, does not involve “skipping over” the times tables) have the best of intentions for your children. If anything, the teachers who pose the greatest risk to our children’s success are the ones dogmatically maintaining an I-know-best attitude. These are the teachers who are likely to reach the least number of students, with the stubborn mindset that there is only one way to learn.

For more on this topic, I invite you to read articles by Joe Bower and Dave Martin.

Truth and opinion

It is a great disservice—and incredibly frustrating—when people try to pass off their opinions as the truth. Rather than moving toward some higher understanding (i.e., toward some objective truth, if there even is such a thing), it serves to block off all useful conversation and regress into partisanship and bickering.

Most Saturday mornings, I listen to a syndicated radio program called MoneyTalks. The host, Michael Campbell, is based out of Vancouver’s AM news station, CKNW. When I first started listening, I felt that Michael exuded an air of superiority; anything (or anyone) that didn’t agree with his fiscally conservative views would immediately be dismissed as irrational, poorly planned, or even dumb.

Initially, I was indignant: I would change stations or turn the radio off. I’ve now gotten to the point where I can listen for the whole show (although it helps that for a lot of it, I’m driving in my car and there’s nothing else to listen to).

There is nothing wrong with having a radio show that advocates fiscally conservative or libertarian views. It is not only Mr. Campbell’s right to advocate the economic and political policies he agrees with, but it is beneficial to all of society to have access to a wide range of different views. But therein lies the problem: Michael Campbell argues his opinions as fact. He denigrates those who disagree with him. Callers to his show simply regurgitate his mantras. (I have yet to hear one caller who disagrees with him; I’m not sure if his producer filters the calls or if only like-minded listeners call in.)

Mr. Campbell has the incredible opportunity to reach and educate a wide audience (and he clearly has a good understanding of what he talks about), but it is being squandered by an inability to recognize his own biases. He constantly passes off his arguments as “free of politicization,” when they are in fact anything but.

Why I’m still in love with Apple

Okay, so perhaps my post from yesterday was a poor attempt at an April Fools’ Day joke. (One of my all-time favourites was Google’s prank from 2013, in which they announced that YouTube was simply a contest and that it would be ending that night.)

In reality, I am extremely happy as an Apple user. I switched to Apple products back when Windows ME was popular (I’m not sure if “popular” is the right word), cell phones were just phones, and integration between software was non-existent. It started with computers, moving from a custom-built Windows desktop to a PowerBook. I would later migrate to an iMac and then a Mac Pro. In 2008, I was required to call 911 after hearing a domestic assault two doors down. In the middle of the call, my Blackberry decided to reboot; I got a spinning hourglass for over 5 minutes. When it finally came back up, I immediately got a call from the 911 operator, who was not too impressed. I got an iPhone later that week, and my migration was complete.

I enjoy not needing to reboot my computer every few days. I love the way things look. Most importantly, I appreciate the way apps work together to make everything seamless. It is this last point that is crucial to me. Over the past few months, I’ve been reconsidering all of the software I use: from productivity to email to my calendar to my word processor. One of my biggest revelations was Alfred, which is hard to describe. It just does everything. (I used to use Quicksilver, which serves a similar purpose and used to be the best program available, but it has fallen to the wayside since being abandoned by its creator.)

Having considered some of my favourite pieces of software, I realized how indispensable some of them are to me. For that reason, I decided I should review them. I’m not talking about the programs I use because they’re the “least worst” version I’ve found (I use Chrome, but it has its faults and I can get by with anything else). I’m talking about the programs I consider to be game-changers: things that make my life more productive, efficient, or secure, and that I could not go without. Some are available on Windows as well. A few are expensive. Others are also (or only) on the iPhone. (You can probably guess a few I have planned by the tags below.) What I hope is that I can encourage someone out there to try some software they otherwise would not have—and become more efficient in the process.


Posts in this series: