I’m a huge fan of science fiction and fantasy. There are few feelings quite as impressive as when an author crafts a world that draws you in (See: Arrakis, Middle Earth, Westeros, LV-246, Hogwarts etc). Perhaps what I find most fascinating though, is how quickly science fiction can turn into real life. For example, the tricorder from Star Trek was a fictional device that could scan different aspects of the environment depending on the requirement, ranging from geological, such as mineral content of rocks, to metereological, such as air pressure and temperature, to biological, such as heart rate and blood pressure. While this sounded like a great dream in the 1960s (when The Original Series aired), we’re now, within a single generation (pun *totally* intended), able to turn this into reality. The new Samsung Galaxy S4, for example, is slated to be released with a suite of health apps (dubbed S Health), including apps to measure heart rate, blood pressure as well as track caloric expenditure. Even things as simple as being able to communicate without needing a bulky cellphone have now become a reality.
As teachers and educators, we suffer from a very real limitation when it comes to teaching. Either due to time, lack of equipment or other constraints we cannot teach some issues the way we would like. But even in the most well-equipped lab, sometimes we can’t teach a concept because the technology doesn’t exist. In those situations, we can use outlandish examples to discuss a concept, and then work backwards from there to discuss the limitations we currently face, a concept called a Thought Experiment. By imagining a scenario, we can push the boundaries of our understanding, discussing the issue from a “what about if X happened,” or “Would Y still occur if A and B happened.” There are many types of thought experiments, and it means different things to different disciplines. I’m going to be using it to refer the use of a metaphor to explain a concept, which corresponds to the “prefactual” type of thought experiment, ie. what outcome would we expect if we had conditions A, B and C.
What to do if your p-value is just over the arbitrary threshold for 'significance' of p=0.05?
You don't need to play the significance testing game - there are better methods, like quoting the effect size with a confidence interval - but if you do, the rules are simple: the result is either significant or it is not.
So if your p-value remains stubbornly higher than 0.05, you should call it 'non-significant' and write it up as such.
Last time I spoke to you about wording and public health, and the unintentional impact that can have on people. I want to continue on that theme today, and talk about what is perhaps one of the most pervasive, and more controversial language choices that we as as a society have made: the military language we use around cancer. Often, the media (and by extension, society) describe someone with cancer as a “warrior” who “battles” cancer. This language isn’t rare, and has been around since the mid-70s when Susan Sontag wrote her book “Illness as a Metaphor.” Research by Seale (2001) states:
News stories commonly feature sports celebrities with cancer, as well as sporting activities by ordinary people with cancer, designed to generate a sense of (usually successful) personal struggle.
My Grade 9 math teacher was a jolly British man, and probably taught me one of the most useful things I ever learnt in high school: how to do basic math in my head (or, since I was in the British educational system, it was Grammar School). Every so often we’d go into our math class and find little bits of paper on every desk. This was a harbinger of doom – it meant we were having a 20 question surprise quiz. And not just any quiz, a mental arithmetic quiz. He would read a question out loud twice, and then we’d have to do the math. He’d give us some leeway (you didn’t have to be exact), but man did I ever hate those quizzes. At the time, they seemed impractical and a colossal waste of time. In retrospect, they were incredibly useful.
Now, being on the other side of the divide, I see something that concerns me. I regularly TA undergraduate and graduate students in statistics, and I notice that many of them, while they have all the skills to do math, are absolutely terrified of it. And as soon as you fear a subject, or don’t want to learn it, you won’t. Your mind will shut down and every instinct you have will prevent you from engaging in the material. As a result, I spend the first hour of any class I’m teaching talking to the students and determining what it is they don’t understand to tailor my sessions accordingly. But the comments generally involve variations on:
“I just don’t get math.”
“I’ve never been any good at math.”
“I don’t like it.”
Of these, the first two concern me. The third I can’t help – I don’t need my students to love math, but I do want them to understand enough to pass the course and feel comfortable interpreting statistical analyses. There’s a culture among schoolkids to dislike math and the perception that it’s largely useless. While in chemistry you can see stuff blow up, and in biology you can dissect animals, math is a largely abstract concept. That perception then manifests as a lack of interest, which results in poorer performance, and that puts people off math.