Testing for Interaction in Binary Logit and Probit Models: Is a Product Term Essential?

By William D. Berry, Jacqueline H. R. DeMeritt, J. Esarey. 2010

428 citations recorded by the source corpus.

Subfields: Political Science and International Relations, Sociology and Political Science, Strategy and Management

View Paper: https://www.semanticscholar.org/paper/f8fda7b20ed2a56b1c569ca0f18a58949c74376f

How researchers see this paper

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

In Political Science and International Relations

In Sociology and Political Science

In Strategy and Management

Citations in the corpus

Estimating logit models with small samples (2021, background): “However, in most cases, using an “S”-shaped inverse-link function (i.e., logit or probit) makes the most theoretical sense, so that marginal effects shrink toward zero as the probability of an event approaches zero or one (e.g., Long, 1997: 34–47; Berry et al., 2010).”
To transform or not to transform: using generalized linear mixed models to analyse reaction time data (2015, background): “…plot only assesses whether there is a significant difference in the linear effect of frequency on the model transformed scale (x-axis), and does not assess whether significant (linear) differences exist on the original RT scale (y-axis) unless the identity link was specified (Berry et al., 2010).”
Does Economic Inequality Depress Electoral Participation? Testing the Schattschneider Hypothesis (2010, background): “Indeed, in nonlinear models the marginal effect of one variable on the probability of an outcome may depend in substantively important ways on the value of another variable even in the absence of a statistically significant coefficient estimate for the product of these two variables: whether a produ”
The Effect of Organizational Characteristics on the Appointment of Nonfamily Managers in Private Family Firms (2015, background): “To interpret the results, the calculation of marginal effects is of great importance as it is perfectly possible that these effects are significant for relevant values of the moderating variable, even if the coefficient on the interaction term is insignificant (Berry et al., 2010; Brambor et al., 20”
Testing Moderating Hypotheses in Limited Dependent Variable and Other Nonlinear Models (2012, background): “See Berry, DeMeritt, and Esarey (2010) for further discussion of this issue.”
Knowledge stocks, knowledge flows and innovation: Evidence from matched patents and innovation panel data (2015, methodology): “Post-estimation issues arise in the derivation of appropriate marginal effects in both the probit and tobit models given the inclusion of squared terms (on knowledge search) and interaction terms (Norton et al. 2004; Hoetker 2007; Berry et al. 2010).”
Marginal Effects in Interaction Models: Determining and Controlling the False Positive Rate (2018, background): “is hard to exaggerate the impact that the methodological advice given in Brambor et al. (2006) has had on the discipline: The article has been cited over 3,300 times as of August 2016.”