I’ve been writing lately on what to do when people who make decisions in an organization say they want data-driven capabilities but then ignore or attack the results of data-driven analysis for not saying what they think the data ought to say. Some of the most productive things you can do in that situation include 
My previous post on how to transform an organization into a more data-driven version of itself made a pretty big assumption that often doesn’t hold true. I assumed that people in the organization wanted their company or agency to become more data-driven. I think almost everyone says they want that if asked. I even think 
Around two years ago, I suddenly realized my statistical training had a great big Bayes-shaped hole in it. My formal education in statistics was pretty narrow – I got my degree in anthropology, a discipline not exactly known for its rigorously systematic analytic methods. I learned the basics of linear models and principal components analysis 
I became interested in sentiment analysis a few months ago as a matter of pure practicality. The company I work for does a lot of customer-satisfaction surveys. Respondents rate various aspects of our products, but they also have the opportunity to ans...
[UPDATE: I just wrapped AspellCheck() in a llply/laply wrapper from Hadley Wickham's `plyr` package, so now it can be run on a vector of texts as well as a single character string, and it now has a default progress bar (set progress = "none" to turn it...
In my previous post, I wrote about ways scale choice could distort the ways survey results portray the things they are supposed to measure. This certainly isn’t a new issue – researchers who use surveys often go to great lengths to ensure that their surveys are valid and reliable, which in this context usually means 
This is a long post. My previous posts have mostly been about my thoughts on various research subjects. This one reports an actual analysis. If you don’t want to read the whole thing, here are the highlights: We really need to stop using surveys so much. If we have to use surveys, it’s probably best 
Zero Inflated Models and Generalized Linear Mixed Models with R.
Zuur, Saveliev, Ieno (2012).
