Monthly Archives: February 2018

PMean: Sentiment analysis of A Christmas Carol

I was at an interesting talk about sentiment analysis and decided to try something simple myself. Sentiment analysis is a text analytics method that compares text data with a list of words with positive or negative sentiments. The relative frequency of the positive or negative words is a crude measure of the general sentiment of the text item. I ran a sentiment analysis on the text of the famous Charles Dickens novel, A Christmas Carol. Continue reading

Recommended: An introduction to implementation science for the non-specialist

I’ve done a lot of work with Evidence-Based Health, but one big and largely unsolved problem is how to get health care professionals to change their practices once the evidence for these changes becomes obvious. If no one changes in the face of evidence, then all the effort to produce and critically appraise the evidence becomes worthless. A new field, implementation science, has been developed to get at methods to encourage the adoption of new evidence-based practices. This paper outlines how implementation science is supposed to work and offers two real world examples of implementation science studies. Continue reading

PMean: Do you need to name your function arguments in R?

If you program anything in R, you’ll end up calling a lot of functions. You pass your data or your constants to these functions, and you can do it in one of two ways. You can either pass the data/constants in the order in which the function expects the arguments or you can match each data/constant value with a particular argument name. This came up in the context of a question: do I need to save everything using


or can I save it with

save.image(“foo.RData”)? Continue reading