Like some of the other terms in our list--level and beta--GLM has two different meanings. It's a little different than the others, though, because it's an abbreviation for two different terms: General Linear Model and Generalized Linear Model. It's extra confusing because their names are so similar on top of having the same abbreviation.
Solomon Hsiang writes: One of my colleagues suggested that I send you this very short note that I wrote on a new approach for displaying regression result uncertainty (attached). It’s very simple, and I’ve found it effective in one of my papers where I actually use it, but if you have a chance to glance [...]
I’ve been interviewed twice in the last year: For DecisionStats, 9 August 2012. For Data Mining Research, 21 October 2011. Republished in Amstat News, 1 December 2011. Some readers of this blog might find them interesting. I said a few things in t...
I've seen analyses of Fisher's iris data so often that sometimes I feel like I can smell the flowers' scent. However, yesterday I stumbled upon an analysis that I hadn't seen before. The typical analysis is shown in the documentation for the CANDISC procedure in the SAS/STAT documentation. A (canonical) [...]
If you find this blog helpful (or even if you don’t but you’re interested in blogs on research issues and tools), there are a few other blogs about doing research that you might find useful. Here are a few that I read. Patter — Pat Thomson. The ...
Our first outgrowth of “Deconstructing Larry Wasserman”. Aris Spanos – Comments on: “Low Assumptions, High Dimensions” (2011) by Larry Wasserman* I’m happy to play devil’s advocate in commenting on Larry’s very interesting and provocative (in a good way) paper on ‘how recent developments in statistical modeling and inference have [a] changed the intended scope of [...]
I always wondered what went on there. $380 x 500 people, that’s $190,000! I’ll have to remember to ask for more money next time I’m asked to speak for a commercial organization.
Editor’s Note: This is the counterpoint in our series of posts on the value of abstraction in graduate education. See Brian’s defense of abstraction on Monday and the comments on his post, as well as the comments on our original teaser post for mor...
Somebody asked me to speak sometime at a data visualization meetup. I think I spoke there a year or two ago but I could do it again. Last time I spoke on Infovis vs Statistical Graphics, this time I could just go thru the choices involved in a few zillion graphs I’ve published over the [...]
Howard Wainer points me to a thoughtful discussion by Moti Nissani on “Psychological, Historical, and Ethical Reflections on the Mendelian Paradox.” The paradox, as Nissani defines it, is that Mendel’s data seem in many cases too good to be true, yet Mendel had a reputation for probity and it seems doubtful that he had a [...]
John Cook's discussion at Wrong and unnecessary — The Endeavour and the comments to that post are all worth reading (I rarely say that about comments to a post). The post is ostensibly on whether a linear model is useful even though it is no, in the ...
Meter Objects [meterobjects.org], developed by Patrick Kochlik and Monika Hoinkis, questions the nature of the whole self-monitoring (also known as the 'quantified self') movement. The carefully designed collection of objects aims to embrace the act o...
Ole Rogeberg writes: After reading your recent post, I thought you might find this interesting – especially the scanned interview that is included at the bottom of the posting. It’s an old OMNI interview with Walter Stewart that was the first thing I read (at a young and impressionable age ;) about the prevalence of [...]
I was asked by a reader how I created Figure 7.2 of the book, reproduced at right, which shows the progression of discrete position probabilities at each step in a simple Metropolis algorithm. I couldn't find the original program, so I made a new one, ...
I don’t know if you have seen this about a person who’s iCloud account was hacked. But man does it freak me out. As a person who relies pretty heavily on cloud-based storage devices and does some cloud-computing based research as well, thi...
R.I.P. R.I.P. Restricted Isometry Property, Rest In Peace Larry Wasserman The restricted isometry property RIP is a critical property in the area of compresses sensing. (See Candes and Tao 2005, Candes, Romberg, and Tao 2006, Donoho 2006). But the RIP assumption has leaked into regression. In this post, I’ll argue that RIP is a theoretical [...]
Attention conservation notice: A call for academic papers on what entropy can say about the origins of life, two subjects you almost certainly don't care about. Well, not exactly for: Special Issue of Entropy: Equilibrium and Non-Equilibrium Entrop...
David Karger writes: Your recent post on sharing data was of great interest to me, as my own research in computer science asks how to incentivize and lower barriers to data sharing. I was particularly curious about your highlighting of effort as the major dis-incentive to sharing. I would love to hear more, as this [...]
I discuss a problem for those who oppose multiply imputing outcome variables--namely, they use models that "impute" outcome variables all the time!
The Fall semester is coming, which means it is time to log into several stupid systems to be prepared for the new semester. Time and time again I'm annoyed by the bullshit password rules at Iowa State University. I wrote to the IT staff once but no one...
The accomplished graphics team at NYT outdid themselves with this feature on the 100m dash through Olympic history (link). You should really go and check out the full presentation. *** They start with a data table like the one shown...
Attention conservation notice: 2200+ words expounding on some notions from statistical theory about over-fitting, plus describing a paper on some experiments trying to apply these ideas to UW-Madison undergrads, concluding with some speculative nihili...
I want to share a brilliant idea and a great example from the You’re Looking at the Wrong Number post at the GestaltU blog. Today, I will focus on the section of this post that outlines simple steps to improve a typical 60/40 stock/bond portfolio by using risk allocation instead of dollar allocation, and targeting [...]
