Extended Data Fig. 4: Engagement and Political Attitudes. ITT Estimates by Initial Feed Setting: Separately for Republicans and Independents vs. Democrats.
Replication of main-text Fig. 2 separately in the subsamples of (1) self-declared Republicans and Independents and (2) self-declared Democrats. Intention-to-treat (ITT) effect estimates in SD. Left panel: ITT estimates of switching the algorithm on. Right panel: ITT estimates of switching the algorithm off. “Chrono” and “Algorithm” refer to the chronological and algorithmic feeds, respectively. For each outcome, the results of two specifications are reported. In blue: the unconditional estimates with robust standard errors, controlling only for the initial feed setting and, where applicable, pre-treatment outcome levels. In orange: the conditional estimates, controlling for pre-treatment covariates using Generalized Random Forests (GRFs). 90% and 95% CIs are reported. Numerical effect sizes and p-values printed on the figure correspond to the conditional estimates (all tests are two-sided). The unit of observation is respondent. From top to bottom, sample sizes are n = 2659, n = 1059, n = 2659, n = 2659, n = 2452, n = 2452, and n = 2596 for Republican and Independent respondents; n = 2306, n = 2278, n = 2306, n = 2306, n = 2144, n = 2144, and n = 2255 for Democratic respondents. Methods describe the tests. SI Table S2.16 reports the exact numerical point estimates, standard errors, confidence intervals and sample sizes for every specification. Extremely few Democrats think that investigating Trump is unacceptable. All outcomes are standardized. ITT effect estimates separately for Republicans and Independents are shown in SI Fig. S2.11.
