Logistic Regression in Rare Events Data

By Gary King, Langche Zeng. Political Analysis, 2001

4,467 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/5aad2cf82e1717ab101786f14571bb318399da64

How researchers see this paper

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

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

Asymmetry of knowledge spillovers between MNCs and host country firms (2007, background): “…approach defines the appropriate benchmark as being frequency of citation from the citing patents to a set of potentially cited patents that are technologically similar to the actually cited patents from the 7 See Amemiya (1985), Greene (2003) or King and Zeng (2001) for more discussion on WESML.”
Predicting accurate probabilities with a ranking loss (2012, methodology): “King and Zeng (2001) show that the constant in the O ( · ) depends on the imbalance in the classes, meaning that logistic regression can give biased probability estimates when attempting to model a rare event.”
When have we looked hard enough? A novel method for setting minimum survey effort protocols for flora surveys (2008, background): “© 2008 The Authors doi:10.1111/j.1442-9993.2008.01869.x Journal compilation © 2008 Ecological Society of Australia events (Glasserman et al. 1999; King & Zeng 2001 ).”
Multivariate LSTM-FCNs for Time Series Classification (2018, methodology): “For datasets with class imbalance, a class weighing schemed inspired by King et al. is utilized [33].”
Contentious Collective Action and the Breakdown of Authoritarian Regimes (2005, background): “See, for example, Goldstone et al. (2000) and King and Zeng (2001).”
Firth's logistic regression with rare events: accurate effect estimates and predictions? (2017, methodology): “[3], penalization by log-F(1, 1) [4] or Cauchy priors [5], King and Zeng’s ‘approximate Bayesian’, and ‘approximate unbiased’ method [6] and ridge regression.”
Dynamics of Lending-Based Prosocial Crowdfunding: Using a Social Responsibility Lens (2018, background): “Firth models account for such disproportionate distributions in a binary dependent variable (Firth 1993; King and Zeng 2001).”
Foreign Aid and Regime Change: A Role for Donor Intent (2011, neutral): “(King & Zheng, 1999a, 1999b; Tomz, King, & Zheng, 1999).”
The taxman tools up: An event history study of the introduction of the personal income tax (2009, background): “King and Zeng (2001) have developed an estimator that corrects for this bias.”
The Augmented Synthetic Control Method (2018, background): “McCullagh and Nelder (1989) and King and Zeng (2001) show that the MLE for logistic regression can be badly biased when the response is a rare event.”