Estimating overdispersion in non-transformed scores of ANVUR's department ranking procedure: a Beto-multinomial model

Key Points

• Overdispersion was identified in the scores from ANVUR's department ranking procedure, indicating inconsistencies in rankings.
• The analysis utilized a beto-multinomial model to assess the distribution of non-transformed scores effectively.
• Statistical methods revealed significant variations in department rankings across multiple evaluation metrics.
• This finding may highlight potential biases in rankings that need to be addressed for fair evaluations.