As part of the recent discussion on anonymous peer review, several people spoke out in favor of double-blind peer review, where neither the authors nor the reviewers know who the others are. I have thought a lot about double-blind peer review, and I’m not entirely convinced, in particular when it comes to grant applications. While double-blind review might solve certain problems and remove certain biases, it would almost certainly amplify other issues, and whether the net effect would be good or bad is unclear. It would also give more power to people such as editors and program managers who operate outside the blinded process.Read More
One of the key challenges in obtaining a PhD is scheduling a committee meeting. In fact, I think that anybody who has managed to successfully schedule three or four committee meetings probably deserves a PhD just for that feat. After all, getting five professors into the same room at the same time is a tall order. Since scheduling committee meetings is such an integral part of graduate education, there should probably be a class on how to do this successfully. However, I don’t think any such class exists. So maybe this blog post can serve as a substitute.Read More
In a recent blog post, Mick Watson argued that anonymous peer review is bad for science. The post makes a number of insightful and valid points. However, the one point I cannot agree with is that junior scientists don’t need anonymity so they can freely speak their mind without fear of retaliation. Mick Watson argues that retaliation should be a non-issue, and that in the cases where it is not we just have to make it so. Frankly, I think this is simplistic black-and-white thinking. There are so many ways in which a senior person can make a junior person’s life more difficult; I would always recommend my graduate students and postdocs that they review anonymously unless they can write a very positive review.Read More
I had a twitter discussion with ggplot2 author Hadley Wickham on whether or not to include a grid background in plots. He thinks the default should have a grid, I think the opposite. I believe we both agree that grids make sense for some plots and not for others, so this is just a question about defaults. On that issue, we remain in disagreement.
This weekend, I finally spent some time learning R Markdown. I had been aware of its existence for a while, but I had never bothered to check it out. What a mistake. R Markdown rocks! It's hands down the easiest and most elegant method to creating rich documents that contain data analysis, figures, mathematical formulas, and text. And it's super easy to learn. I wager that anybody who has RStudio installed can create a useful document in 30 minutes or less. So if you use R, and you've never used R Markdown, give it a try.
A paper published by PLOS Comp. Biol. this month, Chatterjee et al., The Time Scale of Evolutionary Innovation, espouses ideas that are quite similar in spirit to long-standing creationist arguments. I said as much in a few tweets. After having made these comments, I have spent quite some time thinking this paper over. And I simply cannot convince myself that it makes an important contribution to evolutionary biology. It is possible that there’s something I’m missing, but to me the paper looks like a very convoluted and mathematically dense way of making a few tired, trivial, and maybe even tautological arguments.Read More
It seems that Hadley Wickham, the author of the spectacular ggplot2 library for R, is not content with revolutionizing the world of computational data analysis just once. He keeps doing it. This spring, he released the dplyr package, a package that proposes a grammar of data manipulation. I predict that dplyr will become as important for large-scale data analysis and manipulation as ggplot2 has become for visualization. If you like ggplot2, you will love dplyr.Read More
Lately it keeps happening to me that I try to invite somebody to review a paper and they decline, giving as reason that they have reviewed the paper already for a different journal* and reviewing the paper again would put the authors into a situation of double jeopardy. This got me thinking. Should reviewers really decline for that reason? As reviewer, I've always thought the opposite. For a paper I have reviewed already, if the authors have made a reasonable effort to address my comments and have now chosen a more adequate journal, I can keep my review short and recommend acceptance. Thus, I'm actually preventing a situation of double jeopardy. I keep the authors from facing yet another reviewer with new opinions and requests. So, which is right? Should reviewers recuse themselves if they are asked to review again for a different journal, or should they instead leap at the opportunity and give the authors a break? I'd be interested in your thoughts.
*Where the paper was rejected, presumably.
My previous post on tidy data didn’t at all touch on rule 3, “Each type of observational unit forms a table.” The example I gave had only one observational unit, the weekly temperature measurements. Frequently, however, we have data corresponding to multiple observational units. In this case, it is important that we store them in separate tables, and that we know how to combine these tables for useful analyses.Read More
I came across this nice preprint by Hadley Wickham:
Hadley Wickham (2014). Tidy data. Submitted.
In this preprint, Wickham describes a way of organizing data he calls “tidy.” He then argues that tidy data and tidy tools (that both input and output tidy data) make data analysis much more efficient than any alternative approach can.Read More