How Social Ties with Undocumented Immigrants Motivate Latinx Political Participation

Abstract

Prior research suggests social ties with undocumented immigrants among Latinxs may increase political engagement despite constraints undocumented social networks may introduce. We build on prior research and find across six surveys of Latinxs that social ties with undocumented immigrants are reliably associated with collective, identity expressive activities such as protesting, but not activities where immigration may not be immediately relevant, such as voting. Moreover, we assess a series of mechanisms to resolve the puzzle of heightened participation despite constraints. Consistent with prior research at the intersection of anti-immigrant threat and Social Identity Theory, we find Latinxs with strong ethnic identification are more likely to engage in political protest in the presence of social ties with undocumented immigrants, whereas weak identifiers disengage. We rule out alternative mechanisms that could link undocumented social ties with participation including political efficacy, a sense of injustice, linked fate, acculturation, outgroup perceptions of immigration status, partisan identity, conducive opportunity structures, and prosociality. Our contribution suggests the reason social ties with undocumented immigrants are not necessarily a hindrance to political engagement among Latinx immigrants and their co-ethnics is because they can draw from identitarian resources to overcome participatory constraints.

Keywords: Latino politics; immigration; political participation; political psychology; race and ethnic politics; social identity theory.

Figure 1.

Panels A/B characterize the association between undocumented social ties and protest/voting: (A) protest outcome and (B) vote outcome. The x-axis is the standardized undocumented ties coefficient. Meta-analytic estimates are from a pooled random-effects model using the Hartung-Knapp-Sidik-Jonkman method. The red line is the meta-analytic point estimate. Sample size differences between protest and vote outcomes are because the voting item was only asked of registered voters. All estimates are from linear models. Displayed are 95% confidence intervals from heteroskedasticity-consistent robust errors (HC2). SOMOS = SOMOS-Unidos National Survey of Latinos, LDEE = Latino Decisions Election Eve; LDMS = Latino Decisions Midterm Survey; CMPS = Collaborative Multiracial Post-election Survey; LNHIS = Latino National Health and Immigration Survey; RV = robustness value.

Figure 2.

Predicted values conditional on undocumented social ties and Latinx identity (Collaborative Multiracial Post-election Survey). Panel A is the predicted agreement with the notion that anti-immigrant sentiment is anti-Latinx sentiment. Panel B is the predicted protest probability. Panel C is the predicted support for pro-immigrant activism. Panel D is the predicted probability of (validated) voting. The x-axis denotes undocumented social ties. The y-axis is the predicted value. Color denotes Latinx identity (min–max). Annotations denote predicted values. Predicted values are from fully specified models and assume control covariates set at their means and a respondent from California. All estimates are from linear models. All covariates are scaled from 0 to 1. Presented are 95% confidence intervals.