Individual Choice Behavior
By J. Pfanzagl, R. Duncan Luce. 1959
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Yoshua Bengio
- Sergey Levine
- Josh Tenenbaum
- Ruslan Salakhutdinov
- Dacheng Tao
- Trevor Darrell
- Percy Liang
- Pieter Abbeel
Citations in the corpus
- Counterfactual inference for consumer choice across many product categories (2019, methodology): “the following sections. 4.2.2 Multinomial Logit The simplest and most commonly used discrete choice model is the multinomial logit (Train, 2016), which has a long history in economics tracing back to Luce (1959) and McFadden (1974). We focus on a baseline specication that controls for household demo”
- Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement (2019, background): “Our Stochastic Beam Search is a principled alternative that shares some of the benefits of these heuristic variants, such as the ability to control diversity or produce randomized output.”
- Learning From Others (2012, unknown): “This idea is formalized via Luce’s choice axiom (Luce, 1959),”
- A choice experiment on fuel taxation and earmarking in Norway (2011, methodology): “According to the Random Utility Model (RUM) (Luce, 1959; McFadden, 1973) any respondent’s (called respondent i) preferences can be represented by a utility function Ui that is decomposed into a deterministic element (V), which is typically specified as a linear index of the attribute vector (X) of t”
- On the Empirical Content of Quantal Response Equilibrium (2008, unknown): “Dagsvik (1994), McFadden and Train (2000), and Joe (2001) consider related problems of choosing distributions from particular families to approximate choice probabilities (they also consider variation in the set of choices and/or choice characteristics).”
- A modern Bayesian look at the multi-armed bandit (2010, background): “Softmax learning [22] is a randomized strategy that allocates observation t+1 to arm a with probability w̃at = exp( at/ ) ∑k j=1 exp( j t/ ) , (9)”
- Extended discrete choice models : integrated framework, flexible error structures, and latent variables (2001, background): “Second is the concept of random utility theory originated by Thurstone ( 1927) and further developed by Marschak (1960) and Luce (1959). Whereas classic consumer theory assumes deterministic behavior.”
- Best-worst scaling: theory and methods (2014, methodology): “For instance, the Luce choice model corresponds to the MNL model when the latter is written in terms of b = e; b is shown to be a ratio scale in Luce (1959), which implies that u is a difference scale.”
- One and Done? Optimal Decisions From Very Few Samples (2014, methodology): “On our account, this literal “probability matching” behavior amounts to making decisions based on one sample, while decisions based on more samples would correspond to Luce choice decisions with an exponent greater than 1 (Luce, 1959).”
- A choice model with infinitely many latent features (2006, methodology): “Psychologists have long been interested in the mechanisms underlying choice behavior (Luce, 1959).”