DeepAI AI Chat
Log In Sign Up

Statistical Significance and Effect Sizes of Differences among Research Universities at the Level of Nations and Worldwide based on the Leiden Rankings

by   Loet Leydesdorff, et al.

One can use the Leiden Rankings for grouping research universities by considering universities which are not significantly different as a homogeneous set. Such groupings reduce the complexity of the rankings without losing information. We pursue this classification using both statistical significance and effect sizes of differences among 902 universities in 54 countries, we focus on the UK, Germany, and Brazil as national examples. Although the groupings remain largely the same using different statistical significance levels, the resulting classifications are uncorrelated with the ones based on effect sizes (Cramer's V < .3). Effect sizes for the differences between universities are small (w <.2). The results based on statistical-significance testing can be understood intuitively. However, the results based on effect sizes suggest a division between a North-Atlantic and an Asian-Pacific group. The more detailed analysis of universities at the country level suggests that distinctions between more than three groups of universities (high, middle, low) are not meaningful.


page 14

page 16

page 18

page 19

page 22

page 28

page 29

page 33


Are University Rankings Statistically Significant? A Comparison among Chinese Universities and with the USA

Purpose: We address the question of whether differences are statisticall...

Analyzing the disciplinary focus of universities: Can rankings be a one-size-fits-all?

The phenomenon of rankings is intimately related with the government int...

A Note on the Significance Adjustment for FA*IR with Two Protected Groups

In this report we provide an improvement of the significance adjustment ...

Detection of statistically significant differences between process variants through declarative rules

Services and products are often offered via the execution of processes t...

Self-Calibrating the Look-Elsewhere Effect: Fast Evaluation of the Statistical Significance Using Peak Heights

In experiments where one searches a large parameter space for an anomaly...