Quality Entertainment

Okay, so just the word "Statistics" seems to send shivers down the spines of many, while making others feel naseous, anxious, or even violent.

I definitely fall in to the "anxious" category. As such, I appreciate any opportunity to make statistics more lighthearted and/or accessible.

One of my new favorite sources for that is Dr. Andy Field. His website, Statistics Hell, is just the beginning. This man has a talent for making statistics at the very least less intimidating. For example, in the book How to design and report experiments (Sage 2003, co-authored by Graham Hole), there's a chapter about population samples and the purpose of a sample mean. Rather than presenting just the equations and run-of-the-mill examples, the example these authors choose goes something like this: "Imagine we were interested in how many units of alcohol it would take a man before they would snog a Labrador called Ben. Just suppose that in reality, if we tested every man on the planet we'd find that it takes them 10 units on average (about 5 pints of lager) before they would snog dear old Ben."
the authors then proceed to give a clear, valid, detailed explanation of how to calculate the sample means of different populations and plot the respective frequency distributions to yield the sampling distribution, etc., etc., variability, etc., etc.

Later in the book, in the section to help determine which statistical test is most appropriate for your data (which includes a WONDERFUL flow chart), the authors ask, "Are people who watch 'Star Trek' more optimistic about the future of humanity than people who don't?" and use this question to construct a hypothetical study, complete with types of data collected, study design, analysis techniques, etc.

Just for further example, another of Field's popular books is titled Discovering Statistics Using SPSS (and sex, drugs, and rock 'n' roll). It's a more technical, more complex read, but I am still finding it manageable (& far less frustrating) - and, again, part of this is helped by lightening up the technical jargon with some humorous examples. For example, in introducing logistic regression, the example is looking at variables predicting whether a person is male or female. The variables in question? Laziness, pig-headedness, alcohol consumption, and number of burps per day. "So, if we picked a random person and discovered they scored highly on laziness, pig-headedness, alcohol consumption and the number of burps, then the regression model might tell us that, based on this information, this person is likely to be male." There are plenty of "real" and/or "serious" research questions as well, which helps even more - introduce with the lighter, relatable stuff, and then get down to business. And I LOVE the decision trees (also in the sex, drugs, & rock 'n' roll book) because I am constantly second-guessing which test to use.

Mmhmm.

Anyway - I'm just happy to find some resources that make statistics easier to digest so thought I'd share. Hope someone out there can enjoy!