Data from: Prolific observer bias in the life sciences: why we need blind data recording
Data files
Jul 15, 2015 version files 523.65 MB
-
Evolution literature review data.csv
50.65 KB
-
Exact p value dataset.csv
6.47 MB
-
journal_categories.csv
217.11 KB
-
p values data 24 Sept.csv
515.57 MB
-
Proportion of significant p values per paper.csv
1.32 MB
-
Quiz answers - guessing effect size from abstracts.csv
2.96 KB
-
R script to filter and classify the p value data.R
10.38 KB
-
R script to statistically analyse the p value data.R
8.40 KB
-
README.txt
11.75 KB
Abstract
Observer bias and other “experimenter effects” occur when researchers’ expectations influence study outcome. These biases are strongest when researchers expect a particular result, are measuring subjective variables, and have an incentive to produce data that confirm predictions. To minimize bias, it is good practice to work “blind,” meaning that experimenters are unaware of the identity or treatment group of their subjects while conducting research. Here, using text mining and a literature review, we find evidence that blind protocols are uncommon in the life sciences and that nonblind studies tend to report higher effect sizes and more significant p-values. We discuss methods to minimize bias and urge researchers, editors, and peer reviewers to keep blind protocols in mind.