2. Average Predictive Comparisons for Models with Nonlinearity, Interactions, and Variance Components

151 citations recorded by the source corpus.

How researchers see this paper

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

Splitting a Predictor at the Upper Quarter or Third and the Lower Quarter or Third (2009, methodology): “Compared to continuous data, binary data represent even clearer candidates for simple comparisons, since logit and probit coefficients are themselves difficult to interpret on the scale of the data (see, e.g., Gelman and Pardoe 2007).”
Scaling regression inputs by dividing by two standard deviations (2008, background): “We also hope these ideas could also be applied to predictive comparisons for logistic regression and other nonlinear models (Gelman and Pardoe, 2007), and beyond that to multilevel models and nonlinear procedures such as generalized additive models (Hastie and Tibshirani, 1990).”
Public Opinion and Foreign Aid Cuts in Economic Crises (2016, background): “Without exception, they are in the range recommended by Gelman et al. (2014). Details on the convergence diagnostics are available from the authors.”
Key Results of Interaction Models with Centering (2011, methodology): “A natural extension to this method is Gelman and Pardoe (2007), where regression coefficients are augmented with a new measure, average predictive comparisons, obtained as the mean value of the predictive comparison over some specified distribution of the inputs and parameters.”