The treatment of ties in ranking problems.

By M. Kendall. 1945

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark (2019, methodology): “We measure the agreement between these ranking strategies using the Kendall rank correlation coefﬁcient (Kendall, 1945).”
A Survey on Neural Architecture Search (2019, methodology): “h. We then calculate the correlation between the validation error observed on the over-parameterized network and that after training the architecture using the Kendall Tau Rank Correlation Coecient (Kendall, 1945). We note no correlation between these two variables (correlation of 0.12 with a p-valu”
State of What Art? A Call for Multi-Prompt LLM Evaluation (2023, background): “…Kendall’s τ : estimates the agreement between two specific instruction templates which induce rankings R 1 , R 2 over n LLMs, formally defined as (Kendall, 1945): Where P is the number of concordant pairs, Q is the number of discordant pairs, T is the number of ties in the first ranking, and U…”
The Visual Task Adaptation Benchmark (2019, methodology): “We measure the agreement between these ranking strategies using the Kendall rank correlation coefficient (Kendall, 1945).”
A survey of top-k query processing techniques in relational database systems (2008, background): “The Kendall tau distance measures the amount of disagreement between two rankings by counting the number of pairwise disagreements [Kendall 1945].”
D3R grand challenge 4: blind prediction of protein–ligand poses, affinity rankings, and relative binding free energies (2019, methodology): “5 evaluated in terms of the ranking statistics Kendall's t [53, 54], Spearman’s ρ [55], and the centered root-mean-square error (RMSEc) for the free energy sets, recomputed in 10,000 rounds of resampling with replacement to generate error bars based in experimental uncertainty following the same pro”
Last among equals: a comparison of innovation in construction, services and manufacturing in the UK (2005, background): “A value at 0 signifies a statistical independence between two variables (Kendall, 1945).”
Evaluating Recommendation Systems (2011, methodology): “In such cases, rank correlation measures such as Spearman’s ρ or Kendall’s τ [30, 31] can be used.”
Video Summarization Using Deep Neural Networks: A Survey (2021, methodology): “The user-generated frame-level importance scores for the TVSum videos are considered as rankings, and two rank correlation coefficients, namely Kendall τ [104] and Spearman ρ [105] coefficients, are used to evaluate the summary.”
Overcoming Multi-Model Forgetting in One-Shot NAS With Diversity Maximization (2020, background): “Figure 3 presents the Kendall Tau ( τ ) metric [16, 36] the normal loss function presents poor supernet predictive ability, which obtains τ = 0 .”
A Primer on Copulas for Count Data (2007, background): “This problem was recognized very early on; see, e.g., Hoeffding (1940) or Kendall (1945).”
NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size (2020, background): “We also show the Kendall rank correlation coefficient [48] across different datasets in Figure 6.”
CLIP-It! Language-Guided Video Summarization (2021, background): “[26] and report results on rank based metrics, Kendall’s τ [15] and Spearman’s ρ [49] correlation coefficients in the Supp.”
AggGen: Ordering and Aggregating while Generating (2021, methodology): “• Kendall’s tau (τ ) (Kendall, 1945) is a ranking based measure which we use to evaluate both ordering and aggregation.”