Return of the Statistics Blogs

When I shared a few of my favorite statistics blogs over a year ago, Thomas Lumley self-promoted his blogs in the comments, and I’m so glad he did! He is the ringleader and a contributor to the University of Auckland statistics department blog StatsChat, and his personal blog, Biased and Inefficient, has some not-quite-Stats-Chattable posts that can be a lot of fun. Last time I wrote about statistics blogs, I found a great one to follow. Will lightning strike twice?

Image: xkcd.

Image: xkcd.

Lumley is particularly interested in the way the media reports medical statistics. Recently, he wrote about the cancer study that has been going around with headlines like “Most Cancers May Simply Be Due to Bad Luck.” He also expands on some of the data in a supplemental post on Biased and Inefficient. Overall, he is critical of the hype but says that the study itself was important.

In contrast, some of the articles he discusses are quite silly: using lipstick during pregnancy, charging your cellphone in your bedroom (if you are a rat and the cell phone is the absence of melatonin), and eating chocolate to help your memory. It’s a bit depressing to see the same errors over and over, but the critiques can be enlightening and funny. I also appreciate his interesting comments about data visualization. Caution: last link includes objects that look like 3-d pie charts (but aren’t) adorning a tree for no apparent reason. Click at your own risk.

Another statistics blog I’ve been reading lately is A Little Stats, written by statistics teacher Amy Hogan. I particularly enjoyed her recent post about a few of the words she thinks can be stumbling blocks to people who are trying to “translate” statistics back into their normal vocabulary. She highlighted percent, which was timely for me, having just been annoyed by someone using “percent” for numbers smaller than 100, a practice I find unhelpful and somewhat deceptive. Hogan doesn’t mention that issue specifically, but I think her comments about some of the other potential pitfalls of percentages are helpful. In the wrong hands, percentages can be very misleading.

It never would have occurred to me to include age on a list of tricky statistics concepts. Age is pretty straightforward, right? Hogan writes, “If someone is 19 years old, for example, it can be confusing as to whether that means the person has finished their 19th year of life or is starting it. Sometimes people round ages, often if asked about the age of a relative. This is further complicated because in different languages how one says his/her age varies. While I don’t think that the true definition of age varies too greatly, good surveys avoid this issue by asking people for their birth date.” It’s such an easy fix, but it’s one I wouldn’t have thought to do.

This entry was posted in Statistics and tagged , , , , , , , . Bookmark the permalink.

2 Responses to Return of the Statistics Blogs

  1. Thomas Lumley says:

    This time I’m going to promote someone else, who is currently in a bit of a hiatus in the hope that he starts again.

    Cosma Shalizi, at CMU, is a reformed physicist, and someone who shares my lack of taste in genre fiction. He was a blogger during the peak of blogging, but seems to have slowed down over the past year.

    A few examples

    * A Rare Blend of Monster Raving Egomania and Utter Batshit Insanity (review of Wolfram’s “New Kind of Science”) http://vserver1.cscs.lsa.umich.edu/~crshalizi/reviews/wolfram/

    * g, a Statistical Myth (on factor analysis and intelligence): http://vserver1.cscs.lsa.umich.edu/~crshalizi/weblog/523.html

    * Projection as a Defense Mechanism for Social Network Models (on the problems with maximum likelihood estimation for an attractive and popular class of models for networks): http://vserver1.cscs.lsa.umich.edu/~crshalizi/weblog/837.html

    * Bayes < Darwin-Wallace (on consistency of Bayesian estimators, via evolution): http://vserver1.cscs.lsa.umich.edu/~crshalizi/weblog/601.html

    * In Soviet Union, Optimization Problem Solves You (a review of "Red Plenty" and a discussion of industrial optimisation algorithms): http://vserver1.cscs.lsa.umich.edu/~crshalizi/weblog/918.html

  2. Amy Hogan says:

    Evelyn, you know I wasn’t even going to include age, because that’s more of a data problem. It is, though, a toughest thing to capture accurately with microdata. An age issue came up just this week with an old AMC problem with my math team. Timely, indeed. Glad to have you as a reader.

Leave a Reply

Your email address will not be published. Required fields are marked *

HTML tags are not allowed.