Coefficients of Determination in Logistic Regression Models—A New Proposal: The Coefficient of Discrimination

By Tue Tjur. 2009

865 citations recorded by the source corpus.

Subfields: Management Science and Operations Research, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/5731059a63f79392a4ea6e6cb956860214bbbdc0

How researchers see this paper

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

In Management Science and Operations Research

In Statistics and Probability

Citations in the corpus

Using latent variable models to identify large networks of species‐to‐species associations at different spatial scales (2016, methodology): “We computed for each species the TjurR2 values (Tjur 2009) for both Predictions 1 and 2 and assessed the importance of species-to-species associations by examining if and how much more accurate Prediction 2 was than Prediction 1.”
An Examination of Restorative Interventions and Racial Equity in Out-of-School Suspensions (2018, methodology): “The ORs of Model 1 (see Table 3) indicate that Black students were more likely than White students (OR = 1.74, p .001, d = 0.31) to receive an OSS (McFadden’s R2 = .15, Tjur’s R2 = .23).”
Seasonal and life-stage variation in the reproductive ecology of a marine apex predator, the tiger shark Galeocerdo cuvier, at a protected female-dominated site (2016, neutral): “The resulting model fit (df = 1; coefficient of discrimination, D = 0.67; Tjur 2009) indicated that T and E 2 had significant predictive value in determining the probability of gravidity in mature sharks (Table 1).”
Measures of Fit for Logistic Regression (2014, background): “But there’s another R2, recently proposed by Tjur (2009), that I’m inclined to prefer over McFadden’s.”
Measuring and predicting the influence of traits on the assembly processes of wood‐inhabiting fungi (2017, methodology): “At the level of resource units, we computed Tjus’s R2j (Tjur 2009) for each species.”
GANalyze: Toward Visual Definitions of Cognitive Image Properties (2019, background): “From left to right: the regression weight, the confidence interval (CI) for that weight, the p-value for statistical significance, and Tjur’s coefficient of discrimination (D), being the regression model’s goodness of fit [26].”
The influence of board characteristics on sustainability reporting Empirical evidence from Sri Lankan firms (2014, neutral): “339) (Tjur, 2009).”
Joint Species Distribution Modeling: Dimension Reduction Using Dirichlet Processes (2017, methodology): “To identify a suitable number of columns we use the Tjur R2 coefficient of determination (Tjur, 2009), which compares the estimated probabilities of presence between the observed ones and the observed zeros.”
Using joint species distribution models for evaluating how species‐to‐species associations depend on the environmental context (2017, background): “mean predicted occurrence probability over occupied sites minus mean predicted occurrence probability over unoccupied sites (Tjur 2009), and (ii)”
How to make more out of community data? A conceptual framework and its implementation as models and software. (2017, background): “The fitted model explained 10% of species occurrences at the tree level (measured by Tjur’s R2 (Tjur 2009), averaged over species) and 60% at the site level (measured as correlation in abundance, averaged over species).”
A general and simple method for obtaining R2 from generalized linear mixed‐effects models (2013, background): “It is also important to realize that the R2 can be large due to predictors that are not of direct interest in a particular study (Tjur 2009) such as the sex effect on body size in our example.”