R as a Real Data Science Tool

03 October 2017

As with any scientific research, an important aspect of my research is the analysis of quantitative and qualitative data representing individuals’ and groups’ identities, attitudes, experiences, and behaviors. In addition to the complex abyss of increasingly complex research methods and statistical procesdures, the myriad technologies available to aide a given data analytic endeavor are both a blessing and curse…^… as are cliched sayings

Take, for example, IBM SPSS Statistics. This software is at the same time incredibly useful, widely used, exceedingly expensive, clunky, easy to learn, and slower than molasses, glitchy, sometimes intuitive, sometimes unintuitive, able to induce confusion about otherwise straight-forward statistical procedures, etc. My first-ever introduction to statistics was via SPSS when I was an undergraduate psychology student, and, primarily due to my extreme level of scientific ignorance at the time, I assumed that the only reason working in SPSS was so horrid was because statistics were simply a necessary evil that sucked the life out of anyone needing to use statistical procedures of any kind. I soon discovered that I was very wrong in this assumption, when I simply stopped relying on SPSS for my statistical analyses and instead started doing a lot of it by hand first and then via the syntax framework within SPSS. At that point, I realized (a) there is so much more to life than pointing-and-clicking, and (b) it wasn’t that statistics were a necessary evil, but that the only tool I was ever given (beyond pencil, paper, and calculator) to approach any statistical analysis was an un-necessary evil in my life. Specifically, I realied that, instead of pointing-and-clicking around SPSS desparately searching for some obscure menu item with an equally obscure and arbitruary icon, simply learning and using syntax put me in control of the program and of my analysis, because I had to tell the program what to do instead of the other way around. I then went on to love statistics, applied and got accepted into my current graduate research program, and, alongside my 10 or so cohort members was introduced to R by Dr. Joel Steele, who took somewhat of a risk by using my cohort as the ‘guinnea-pig cohort’ for his requirement of using R for all statistical procedures conducted in the first-year quantitative data analysis series. While the requirement was lifted after my first term, when enough of my cohort had negative learning experiences they and their advisors attributed to the R requirement, I had already fallen down the Rabbit hole and there was no way in hell I was leaving my newfound wonderland.

So, here we are. I do not consider myself an expert in anything, and in fact more often than not find myself with a Faustian complex: Feeling as though the more knowledge I gain the less I know and the more I want/need to know, except my “hell” is R and there is no Mephistopholis around to even attempt saving me. Did I mention that I also have a B.A. in English? It comes out from time-to-time.


References



     
Design by Rachel ("Riley") Smith-Hunter based on the Tufte CSS theme by Dave Liepmann & Edward Tufte
Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.