RMPW was applied to test whether employment mediated the effect of an experimental welfare-to-work program on maternal depression¶

Claim · All claims
Evidence · 1 study · theoretical r3 · q2
Currency · newest study 2015 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? The RMPW technique was applied to an experimental welfare-to-work program to identify whether employment mediated the program's relationship with maternal depression. → Guanglei Hong 2015

Evidence¶

Guanglei Hong 2015¶

Guanglei Hong, Jonah Deutsch, Heather D. Hill. (2015). Ratio-of-Mediator-Probability Weighting for Causal Mediation Analysis in the Presence of Treatment-by-Mediator Interaction. Journal of Educational and Behavioral Statistics, vol. 40, no. 3. https://www.mathematica.org/publications/ratioofmediatorprobability-weighting-for-causal-mediation-analysis-in-the-presence

q2 · i? · theoretical · r3

An empirical application of RMPW to data from an experimental welfare-to-work program, with employment as the mediator and maternal depression as the outcome; the available text reports the application but no resulting effect estimates.

"We apply the technique to identifying whether employment mediated the relationship between an experimental welfare-to-work program and maternal depression."

Discussion¶

Related Claims¶

• Correct specification of the mediator propensity score models is crucial when parametric RMPW is applied — a broader claim this one bears on
• Conventional mediation methods generate biased results when the mediator–outcome relationship depends on treatment condition — a broader claim this one bears on
• RMPW requires relatively few assumptions about outcome and mediator distributions and outcome-model functional form compared with model-based alternatives — a broader claim this one bears on
• RMPW decomposes total effects into natural direct and indirect effects, with the indirect effect further split into a pure indirect effect and a natural treatment-by-mediator interaction effect — a broader claim this one bears on
• Whether results represent causal effects requires knowledge and assumptions about data, design, and methods in both experimental and non-experimental work — related