Weekly Links, February 26: Scatterplots vs. bar graphs; yes, we get it, your study is novel; RCTs are (not) useful for policy-making: redux, and more...

|

This page in:

David is traveling, so I am in charge of the links, which means the topics will decidedly differ than the usual links and the Friday links will get posted on Friday, instead of Thursday afternoon:
 
  • Many different data distributions can lead to the same bar graph: An article in PLOS Biology gives a warning and suggestion for studies with small sample sizes: “Papers rarely included scatterplots, box plots, and histograms that allow readers to critically evaluate continuous data. Most papers presented continuous data in bar and line graphs. This is problematic, as many different data distributions can lead to the same bar or line graph. The full data may suggest different conclusions from the summary statistics.” The figure below provides a nice example…
 
 
  • Are Scientific Findings Exaggerated? Two psychiatrists and a neuroscientist report, on LSE’s The Impact Blog, a positive trend over time in the use of positive words in abstracts, such as “robust,” “novel,” “innovative,” and “unprecedented,” which increased in relative frequency up to 15000% since the 1970s! The authors’ hypothesis is that “…the emergence of a ‘publish or perish’ culture aimed at productivity and novelty could have affected the use of positive and negative words in scientific reporting and discussion.”
 
  • Speaking of which… A Unicef Innocenti Research Brief on the effects of cash transfers on mental health among youth states: “This study is the first to assess the impact of a large-scale UCT in sub-Saharan Africa on youth mental health and well-being. This adds to evidence from a smaller study that targeted adolescent girls in Malawi and investigated mental health outcomes, but with a conditional cash transfer intervention (Baird, de Hoop and Özler, 2013).” Let’s set aside the caveats that had to be made for this to be the “first” study of its kind (here the key additions, I suspect, are “large-scale” and “youth”). If you even skimmed the cited paper or just read the abstract carefully, it is impossible to call Baird, de Hoop and Özler, 2013 a CCT experiment: the whole point of that experiment is to compare CCTs against UCTs! It’s right there on page 2 of the paper: “The unique design of the intervention allows us to compare the impact of unconditional cash transfers (pure income shocks) with the impact of cash transfers made to families conditional on regular school attendance by the school-age girl in the household.” Unfortunately, this kind of careless reference is far from rare – happens all the time…
 
  • The holy grail in sexual and reproductive health: On Monday, the New York Times reported that a new vaginal ring, which slowly releases a drug called dapivirine, costs about $5 and needs to be replaced only once a month, showed partial effectiveness in two clinical trials – reducing infection rates by 27 and 31 percent. While the much lower than full protection is disappointing, as usual partial compliance is at least partly to blame, the more hopeful news comes in the final paragraph: “Future versions will last three months, she said, and some will combine antiviral medication with birth-control drugs.” Convenient birth control and HIV protection for women in one package that is not a condom? Looking forward to it...
 
 

Authors

Berk Özler

Lead Economist, Development Research Group, World Bank