Statistical conspiracy theory? Here is a link to John Williams’ Shadowstats site and (appropriately) three readings that critique the overall approach. For example, in one reading, it is suggested that the “shadow” in the Shadowstats name consists of an inappropriate modeling methodology.
* “securitization” as a means to fund scientific projects (an interesting experiment in financial engineering).
Welcome to the long tail of science. Today, we have three readings: two on the sharing of “dark data”, and one on measuring “inequality” of citation rates. In [1, 2], the authors introduce us to the concept of dark data. When a paper is published, the finished product typically includes only a small proportion of data generated to create the publication (Supplemental Figures notwithstanding). Thus, dark data is the data that are not used, ranging from superfluous analyses to unreported experiments and even negative results. The authors of  contemplate the potential usefulness of sharing these data.
In the third paper , John Ioannidis and colleagues contemplate patterns in citation data that reveal a Pareto/Power Law structure. That is, about 1% of all authors in the Scopus database produce a large share of all published scientific papers. This might be related to the social hierarchies of scientific laboratories, as well as publishing consistency and career longetivity. But not to worry — if you occupy the long-tail, there could be many reasons for this, not all of which are harmful to one’s career.
Musical Metacognition for July. No colors in this one, and the songs are from the 70’s and 80’s, but note the saxophone in both songs.
Here are some readings on networking and open science from my reading queue. The first is a paper on the life-cycle of a preprint on the arXiv. The top image is Figure 2 in the paper. The other two readings advocate for the use of open access protocols and social media to disseminate research and counter cultural biases towards keeping research behind laboratory doors.
On the genetic architecture of economic and political preferences. Using a SNP analysis, the authors demonstrate that such traits have a polygenic architecture (e.g. many genes, small effect size for each). Studies that are underpowered (and no one knows what the appropriate sample sizes should be) can potentially generate many false positive associations between genes and behavior.
A story that equates (or perhaps confounds) the psychophysiology of political ideologies with the roots of more general ideological bias. Are we really looking at “natural” differences between liberals and conservatives? Or does this simply demonstrate that high-profile social issues with already polar liberal and conservative positions are undergirded by strong emotional responses? The standard evolutionary psychology explanation is a bit contrived as well. But it goes well with the previous article.
Crossmodal and cross-cultural comparisons, unite! In this study, people from several different cultures were asked to make both “congruent” and “incongruent” associations between smells and colors. The authors come to the conclusion that cultural context through experience has both statistical (covariance) and semantic (linguistic) components.