The featured blog is the social science statistics blog. An introduction to the blog is followed by a further article ‘cognitive science’ which discusses the aim of the blog as identifying common themes in statistical analysis amongst different branches of the social sciences. Authors (from Harvard University) include those studying for PhD’s in the social sciences including law and cognitive science and each focuses on a specific area. The blog unsurprisingly covers a wide variety of material with a central theme of social science statistical methods or related material. As the blog has progressed, the articles contain more graphical information illustrating the points being made and even embedded videos. The articles range from easy to understand articles for the statistics novice to more esoteric articles covering statistical niches. At the more generic level there are a number of articles including an intriguing discussion of Occam’s Razor and Evolution, an article on ‘Who Makes A Good Peer Reviewer?’, a review of a study on ‘Running and Aging‘ and how the 0.05 value in significance testing came into being in ‘How 0.05 comes into rule? and Placebo effects and the probability of assignment to active treatment.
A theme that is developed through the blog is that of data sharing and visualisation. The possibility of universal data availability is discussed in data availability and an article on data (non) sharing looks at difficulties that need to be overcome. There are a number of websites that make data available for analysis and these are covered in the blog including a link to datamob which puts up data for analysis, a link to Many Eyes – an IBM website which allows people to upload their data for analysis and a link to Gap Minder which aims to make complex data accessible to the general public. There are a number of methods for representing data including a link to an animations package for representing data, an article on Missingness Maps and Cross Country Data – visualising missing data, an article visualisation for data cleaning, and a link to processing, a programming language for visualising data.
The more specific articles including the ‘Don’t Use Hypothesis Tests for Balance‘ post discusses the disadvantages of hypothesis tests for matching samples, an article on Rosenbaum-Type sensitivity Tests in examining hidden bias and a further continuation of the discussion in ‘Misunderstandings among Experimentalists and Observationalists‘. There are also helpful articles on relevant programming languages or online resources including the BLOG inference engine – a programming language that is used to produced structures and objects and allows probabilistic inferences from the generated models (this sounds like a very intuitive way of creating certain types of mathematical models), Tools for Research (A Biased Review) (which is a useful review of open source and other types of programs for research), an inauthentic paper detector and the Google Trends function is examined in A Bit of Google Frivolity.
This blog is regularly updated and contains a variety of interesting articles on social sciences statistics. While this topic sounds a little dry superficially, the articles are engaging and the material is relevant to the social sciences. The blog is particularly suited to those who are interested in or already carrying out research in the social sciences.
If you have any comments, you can leave them below or alternatively e-mail firstname.lastname@example.org
The comments made here represent the opinions of the author and do not represent the profession or any body/organisation. The comments made here are not meant as a source of medical advice and those seeking medical advice are advised to consult with their own doctor. The author is not responsible for the contents of any external sites that are linked to in this blog.