Effect Displays in R for Multinomial and Proportional-Odds Logit Models: Extensions to the effects Package

By John Fox, Jang-Pyo Hong. 2009

356 citations recorded by the source corpus.

Based on recent work by Fox and Andersen (2006), this paper describes substantial extensions to the effects package for R to construct effect displays for multinomial and proportional-odds logit models. The package previously was limited to linear and generalized linear models. Effect displays are tabular and graphical representations of terms — typically high-order terms — in a statistical model. For polytomous logit models, effect displays depict fitted category probabilities under the model, and can include point-wise confidence envelopes for the effects. The construction of effect displays by functions in the effects package is essentially automatic. The package provides several kinds of displays for polytomous logit models.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/c10c3480d40eda6dadeef17687c2840aa26679d6

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

Visualizing Fit and Lack of Fit in Complex Regression Models with Predictor Effect Plots and Partial Residuals (2018, methodology): “The extension to predictor effect displays is implemented for linear and generalized linear models of arbitrary complexity in the current version of the effects package for R (Fox 2003; Fox and Hong 2009; Fox, Weisberg, Friendly, and Hong 2018a), which we use to generate the illustrations in the pap”
Least-Squares Means: The R Package lsmeans (2016, methodology): “As a side note, the effects package (Fox 2003; Fox and Hong 2009) provides an alternative way to analyze these data:”
Visualizing Count Data Regressions Using Rootograms (2016, neutral): “Unlike other model-based graphics that often focus on effects on the mean of the fitted distribution (e.g., effect displays, Fox 2003; Fox and Hong 2009), rootograms capture deviations across the support of the entire distribution and hence can help diagnosing misfit regarding scatter and/or shape.”