Interaction Terms in Nonlinear Models

Abstract

It is important to understand why interaction terms are included in nonlinear models in order to be clear about their substantive interpretation.

Health consequences of the US Deferred Action for Childhood Arrivals (DACA) immigration programme: a quasi-experimental study

“…The difference-in-differences estimate (both in linear and non-linear models 35 ) is denoted by the coefficient on the product term (β 1 ). This estimate can be interpreted as the effect of the policy on DACA-eligible individuals before versus after the policy change, compared with the effect on DACA-ineligible individuals.…”

Mammography Use Among Women Ages 40–49 After the 2009 U.S. Preventive Services Task Force Recommendation

“…Standard errors were adjusted to account for non-independence of observations within states. 26 The results of the logistic regression models were used to calculate predicted probabilities of mammogram use by age group within each year, adjusting for access to care, education, race and ethnicity, and health status.…”

Job insecurity and financial distress

“…how the effect of one variable changes when another variable changes) do not provide the change in the partial effect of the variables on the conditional mean function and care needs to be used to interpret the results (Ai and Norton (2003), Greene (2010), Karaca-Mandic et al (2011)). In addition, in some cases, the results of hypothesis tests are an artifact of the functional form and do not necessarily have an economically meaningful content (Greene (2010)).…”