This is my first statistics blog, in fact, my first blog ever. So I want to start at a very basic level in dealing with the general question of student motivation in statistics classes. When I was a young professor in the Psychology Department, in spite of loving to teach statistics, I was the only one willing to argue that a statistics course should not be required of all psychology majors. I was aware that most majors did not want to take statistics, and thought maybe they were right. Statistics can be viewed as a technical subject matter needed by researchers or those who need to read and evaluate the research literature. My view was that if a student did not follow a career in psychology, as many would not, then taking statistics courses would be wasteful and unpleasant. The appropriate time for such technical learning was graduate school. My own experience supported this view. I believe I was the only student in my graduate program who had not had a statistics course as an undergraduate, yet I stood at the top of my first year graduate statistics courses and did not feel I had been at a disadvantage. (Of course, the quality of undergraduate statistics courses then was not what it is today.)
But the rest of the department agreed unanimously that there should be a required statistics course for undergraduate majors. Over the years I taught that course I realized that I thought of statistics not just as a technical exercise for professionals, but as a way of dealing with more general issues, and eventually I tried to communicate that to my students in hopes that it would make the subject matter more meaningful and so more interesting.
So I told the students at the beginning of the course that they probably thought of this statistics course as a narrowly conceived and pretty much useless requirement. On the contrary, I argued, this is probably the broadest course they would ever participate in, since it dealt with one of the fundamental characteristics of the entire universe: random chance. Contrary to what television CSIs tell us: that there are “no coincidences,” in the real world there are an uncountable number of coincidences. As time goes by an infinite stream of events flows with it; some of these events are related, some cause others, but it is not easy to detect these relationships (the “signal”) in the vast real-world flow of all the other random events (the “noise”). Science is a powerful tool developed to discover and confirm relationships, especially causal, among events. But the role of chance is ever present. One implication is that none of our measurements of anything, psychological (e.g., measures of intelligence, anxiety, etc.) or physical (e.g., length of a snake jaw bone, reaction time to a signal) is perfect. All measurements are contaminated with “error.” (Here I would give some examples: (1) Early recognition of measurement error by human observers in the field of astronomy: different observers could not agree on the timing of celestial events. (2) The data that provided “proof” of Einstein’s theory by confirmation of his prediction that light should bend in gravitational fields (i.e., as it passed near the sun) did not precisely fit the numerical prediction made by the theory). If we cannot trust the accuracy of our observations and measurements, how can we ever learn anything? Believe it or not, I would tell them, this statistics course attempts to deal with this fundamental randomness of the universe. We will find ways to measure the amount of error in our measurements, and by doing so, try to draw conclusions about, in particular, cause and effect relationships. This process will necessarily involve issues of “experimental design” (the name of the course, at least for some years, was “Experimental Design and Statistical Analysis”). You might even be able to apply your new understanding of randomness in the universe to your everyday lives.
And that was my attempt to interest students in the content of the statistics course. Did it work? For one (!) student at least, a very bright student who later became one of my Apprentice Teachers in statistics; he mentioned later that in that first lecture he had thought, “Aha, this sounds promising.”