Home institution bias in the New England Journal of Medicine? A noninferiority study on citation rates

Abstract

Recently, in the four top journals of humanities, an institutional bias towards publication of authors from Harvard and Yale was shown. The New England Journal of Medicine (NEJM) is today the highest ranked general medical journal. It is unknown if there exists institutional bias favoring publication of articles originating from Harvard University, since the NEJM is produced by the Massachusetts Medical Society with close connections to the Harvard University. We examined if studies originating from the Harvard University published in the NEJM were noninferior in terms of citation rates compared to articles with an origin outside Harvard University. We evaluated original research articles published in the NEJM in 2000 up until June 2001. A two-sample noninferiority test based on the primary endpoint of citations was performed. Twenty-two studies were affiliated to the Harvard University and 280 studies were not affiliated to the Harvard University. The mean number of citations for Harvard affiliated studies was 625 (95% CI 358-952, median 354) and for non-Harvard affiliated studies 493 (95% CI 421-569, median 303). The mean difference was not statistically different between affiliations, but fulfilled the requirements for noninferiority [132 (95% CI - 138-402, P = 0.343), Δ 200]. In summary, citation rates were comparable between studies origination from the Harvard University compared to non-Harvard Institutions. Based on these results there appears to be low risk of institutional bias in the publishing process of original studies in the NEJM.

Keywords: Academic publishing; Citations rates; Impact of articles; Institutional bias.

Fig. 1

a Box and whiskers plot show median citations indicated by the vertical line and the interquartile range indicated by the box, with whiskers containing 1.5 times the interquartile range and outliers indicated by individual dots. Citation data is stratified for institutional affiliation: Harvard or non-Harvard. b Back to back histogram show the distribution of citations stratified for institutional affiliation: Harvard or non-Harvard. Each histogram depicts the actual per study citations with 22 Harvard affiliated studies on the left side and 280 non-Harvard affiliated studies on the right side distributed on the y axis