Remarks on the method of paired comparisons: I. The least squares solution assuming equal standard deviations and equal correlations

By F. Mosteller. 1951

How researchers see this paper

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

1. Sergey Levine
2. Ziyun Wang
3. Yoshua Bengio
4. Misha Denil
5. Nando de Freitas
6. Trevor Darrell
7. Jitendra Malik
8. Ruslan Salakhutdinov

Citations in the corpus

• A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning (2010, methodology): “This model, relating binary observations to a continuous latent function, is known as the ThurstoneMosteller law of comparative judgement [Thurstone, 1927, Mosteller, 1951].”
• Dynamic Bradley–Terry modelling of sports tournaments (2013, methodology): “This simple choice model is commonly termed the Bradley–Terry model (Bradley and Terry, 1952) or the Thurstone–Mosteller model (Thurstone, 1927; Mosteller, 1951) depending on whether F is the cumulative distribution function of a logistic or of a standard normal random variable respectively.”
• Ranking soccer teams on basis of their current strength: a comparison of maximum likelihood approaches (2017, background): “EURO2016 or the Africa Cup of Nations 2017) or the confederations cup, and 4 for World Cup matches. 2.2 The Thurstone-Mosteller and Bradley-Terry type models Thurstone-Mosteller (TM) (Thurstone, 1927;Mosteller, 2006) and Bradley-Terry (BT) models (Bradley and Terry, 1952) have been designed to predi”
• A Bayesian interactive optimization approach to procedural animation design (2010, methodology): “It is a classical model for relating bi­ nary observations to a continuous latent function, which is known as the Thurstone-Mosteller law of comparative judg­ment [Thu27,Mos51].”
• Active Preference Learning with Discrete Choice Data (2007, methodology): “Probability models for learning from discrete choices have a long history in psychology and econometrics [Thurstone, 1927; Mosteller, 1951; Stern, 1990; McFadden, 2001].”
• Statistical ranking and combinatorial Hodge theory (2008, background): “There are other plausible choices for defining ¯ Y ij , e.g. [42, 29, 30, 31], but we will not discuss more of them here.”
• Scaling data-driven robotics with reward sketching and batch reinforcement learning (2019, background): “Learning from preferences has a long history [66, 50, 19, 64, 14, 32].”