Hi everyone. I’m Ryan (McManus)! This fall, I started my third year as a graduate student in Boston College’s PhD program in Psychology and Neuroscience. At BC, I’m a trainee in the Morality Lab, where we study moral psychology using a wide range of techniques (e.g., online/in-person surveys, behavioral experiments, economic games, fMRI, and transcranial magnetic stimulation). Although our work is fascinating (you should definitely check it out!), my primary intention for this blog is not to talk about the cool research we do. Rather, I want to use this blog as a space to explore statistics and methods in psychology and to occasionally write about any cool published research I come across.
As an incoming third-year grad student who is done with the required experimental design/stats coursework, part of me feels as though I should have learned all of what I needed to learn by now, and therefore I should focus my time on the literature upon which I’m building my research. But another part of me feels as though, even if I’m done with formal coursework, I should never stop learning and trying to teach myself about statistics and methods. This is because the more I’ve learned about different stats and methods, the more questions I’ve realized are possible to ask and answer. Anyway, that second part of me is what’s motivating this hopefully long-into-the-future blog.
Here are a few ground rules for the blog (that may change depending on the topic covered):
- I will be as non-technical as possible. I don’t see this being a problem. After all, I’m not a statistician/methodologist. I’m not even a quantitative psychologist in training. I’m simply a (still junior) grad student who wants to better understand statistics and methods so that I can make appropriate inferences and catch errors, both in my own work and in others’ work. If I can better understand certain topics myself by doing this, or if I can help at least one other person better understand certain topics by doing this, I will consider this a success. This is more reason, from my perspective, to embrace communicating clearly and in plain language.
- I’m not going to explicitly reference published research if I can help it. For some (and hopefully most) posts, I’m going to rely only on simulating data and making inferences from those simulations that are easily verifiable by anyone who follows along with the shared code. I will, however, give shout-outs to researchers who helped me to understand some concepts in the first place (who I mostly only know because of following them on Twitter). That said, I realize that for some topics, not citing formal research may be practically impossible; I’ll adjust accordingly.
- I’m going to try to respond to any question/comment that I feel equipped to answer, assuming anyone actually reads these things. If I feel like I’m unable to do so, I will say so. If I do feel equipped to respond to a comment/question, I’ll try to! If I end up being wrong, I’ll gladly admit it and use it as a learning opportunity.
- I’ll always try to condense each post into TL;DR (“Too Long; Didn’t Read”) sections for those who are interested enough to read and extract the core ideas, but don’t have enough time to read in detail. These sections will be labeled as TL;DR (bolded in red for quick access).
If you’ve made it this far, I already appreciate your reading 😊. I hope you keep coming back for more! If you have the time and interest to keep reading, the first topic I will cover is statistical power. What is it, why is it important, and how can you teach yourself to better understand it and its implications if you currently feel that you don’t have a solid understanding? Please go to my next post for more info!