241120_002710 zoib results

```r # zero-one-inflated beta regressions m1 <- brm( bf( I(vote_chance_2 / 100) ~ conditionHarris * scale(vote_chance_1) * scale(topicZ), phi ~ conditionHarris * scale(vote_chance_1) * scale(topicZ), zoi ~ conditionHarris * scale(vote_chance_1) * scale(topicZ), coi ~ conditionHarris * scale(vote_chance_1) * scale(topicZ) ), data = d0[lean == initial_lean], family = zero_one_inflated_beta(), chains = 8, iter = 2000, cores = 8 ) m1 > m1 Family: zero_one_inflated_beta Links: mu = logit; phi = log; zoi = logit; coi = logit Formula: I(vote_chance_2/100) ~ conditionHarris * scale(vote_chance_1) * scale(topicZ) phi ~ conditionHarris * scale(vote_chance_1) * scale(topicZ) zoi ~ conditionHarris * scale(vote_chance_1) * scale(topicZ) coi ~ conditionHarris * scale(vote_chance_1) * scale(topicZ) Data: d0[lean == initial_lean] (Number of observations: 1259) Draws: 8 chains, each with iter = 2000; warmup = 1000; thin = 1; total post-warmup draws = 8000 Regression Coefficients: Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS Intercept 1.59 0.08 1.43 1.75 1.00 4105 5376 phi_Intercept 2.06 0.13 1.80 2.30 1.00 4719 5046 zoi_Intercept 0.84 0.11 0.63 1.06 1.00 9811 5964 coi_Intercept 10.00 4.07 4.11 19.65 1.00 2037 1960 conditionHarrisproHarris 0.48 0.10 0.28 0.69 1.00 4671 5610 scalevote_chance_1 0.92 0.06 0.81 1.03 1.00 4151 4851 scaletopicZ 0.05 0.08 -0.11 0.21 1.00 4179 5894 conditionHarrisproHarris:scalevote_chance_1 0.12 0.08 -0.03 0.28 1.00 4550 5567 conditionHarrisproHarris:scaletopicZ -0.10 0.10 -0.30 0.10 1.00 4134 5610 scalevote_chance_1:scaletopicZ 0.06 0.06 -0.05 0.17 1.00 4480 5062 conditionHarrisproHarris:scalevote_chance_1:scaletopicZ -0.10 0.08 -0.25 0.05 1.00 4761 6013 phi_conditionHarrisproHarris 0.93 0.18 0.58 1.28 1.00 5122 5519 phi_scalevote_chance_1 0.12 0.07 -0.03 0.26 1.00 5063 5300 phi_scaletopicZ 0.12 0.13 -0.12 0.38 1.00 4269 5423 phi_conditionHarrisproHarris:scalevote_chance_1 0.41 0.11 0.20 0.62 1.00 5201 5754 phi_conditionHarrisproHarris:scaletopicZ -0.35 0.18 -0.70 0.00 1.00 4360 5736 phi_scalevote_chance_1:scaletopicZ -0.08 0.07 -0.23 0.06 1.00 5210 5948 phi_conditionHarrisproHarris:scalevote_chance_1:scaletopicZ -0.05 0.11 -0.28 0.16 1.00 5525 5762 zoi_conditionHarrisproHarris -0.32 0.17 -0.66 0.01 1.00 7990 5943 zoi_scalevote_chance_1 1.57 0.17 1.26 1.91 1.00 6352 5686 zoi_scaletopicZ 0.01 0.11 -0.21 0.23 1.00 7246 6022 zoi_conditionHarrisproHarris:scalevote_chance_1 0.92 0.32 0.31 1.57 1.00 5841 5497 zoi_conditionHarrisproHarris:scaletopicZ -0.27 0.17 -0.60 0.07 1.00 5751 5980 zoi_scalevote_chance_1:scaletopicZ -0.44 0.17 -0.80 -0.13 1.00 6217 5320 zoi_conditionHarrisproHarris:scalevote_chance_1:scaletopicZ 1.36 0.32 0.77 1.99 1.00 5591 5109 coi_conditionHarrisproHarris 0.64 5.54 -10.67 11.68 1.00 2536 2418 coi_scalevote_chance_1 17.38 9.72 5.82 42.35 1.00 1534 1046 coi_scaletopicZ 1.13 4.13 -7.71 9.15 1.00 1561 1468 coi_conditionHarrisproHarris:scalevote_chance_1 -11.83 9.98 -37.15 1.38 1.00 1570 1056 coi_conditionHarrisproHarris:scaletopicZ -1.38 5.63 -12.34 10.15 1.00 2082 2092 coi_scalevote_chance_1:scaletopicZ -12.20 9.98 -37.92 -0.28 1.01 1476 1081 coi_conditionHarrisproHarris:scalevote_chance_1:scaletopicZ 10.67 10.26 -2.80 36.40 1.01 1499 1103 Draws were sampled using sampling(NUTS). For each parameter, Bulk_ESS and Tail_ESS are effective sample size measures, and Rhat is the potential scale reduction factor on split chains (at convergence, Rhat = 1). > summ(m1) term result p_sig <char> <glue> <char> 1: b_Intercept b = 1.59 [1.43, 1.75] * # mu of beta dist 2: b_phi_Intercept b = 2.06 [1.80, 2.30] * # precision of beta dist 3: b_zoi_Intercept b = 0.84 [0.63, 1.06] * # whether outcome is extreme (0/1) or not (not [0/1]) 4: b_coi_Intercept b = 10.00 [4.11, 19.65] * # if it's 0 or 1, is it 1? (standard logistic) # mu of beta dist (logit scale) 5: b_conditionHarrisproHarris b = 0.48 [0.28, 0.69] * 6: b_scalevote_chance_1 b = 0.92 [0.81, 1.03] * 7: b_scaletopicZ b = 0.05 [-0.11, 0.21] 8: b_conditionHarrisproHarris:scalevote_chance_1 b = 0.12 [-0.03, 0.28] 9: b_conditionHarrisproHarris:scaletopicZ b = -0.10 [-0.30, 0.10] 10: b_scalevote_chance_1:scaletopicZ b = 0.06 [-0.05, 0.17] 11: b_conditionHarrisproHarris:scalevote_chance_1:scaletopicZ b = -0.10 [-0.25, 0.05] # precision of beta dist (log scale) 12: b_phi_conditionHarrisproHarris b = 0.93 [0.58, 1.28] * 13: b_phi_scalevote_chance_1 b = 0.12 [-0.03, 0.26] 14: b_phi_scaletopicZ b = 0.12 [-0.12, 0.38] 15: b_phi_conditionHarrisproHarris:scalevote_chance_1 b = 0.41 [0.20, 0.62] * 16: b_phi_conditionHarrisproHarris:scaletopicZ b = -0.35 [-0.70, 0.00] 17: b_phi_scalevote_chance_1:scaletopicZ b = -0.08 [-0.23, 0.06] 18: b_phi_conditionHarrisproHarris:scalevote_chance_1:scaletopicZ b = -0.05 [-0.28, 0.16] # whether outcome is extreme (0/1) or not (not [0/1]) (logit scale) 19: b_zoi_conditionHarrisproHarris b = -0.32 [-0.66, 0.01] 20: b_zoi_scalevote_chance_1 b = 1.57 [1.26, 1.91] * 21: b_zoi_scaletopicZ b = 0.01 [-0.21, 0.23] 22: b_zoi_conditionHarrisproHarris:scalevote_chance_1 b = 0.92 [0.31, 1.57] * 23: b_zoi_conditionHarrisproHarris:scaletopicZ b = -0.27 [-0.60, 0.07] 24: b_zoi_scalevote_chance_1:scaletopicZ b = -0.44 [-0.80, -0.13] * 25: b_zoi_conditionHarrisproHarris:scalevote_chance_1:scaletopicZ b = 1.36 [0.77, 1.99] * # if it's 0 or 1, is it 1? (standard logistic) (logit scale) 26: b_coi_conditionHarrisproHarris b = 0.64 [-10.67, 11.68] 27: b_coi_scalevote_chance_1 b = 17.38 [5.82, 42.35] * 28: b_coi_scaletopicZ b = 1.13 [-7.71, 9.15] 29: b_coi_conditionHarrisproHarris:scalevote_chance_1 b = -11.83 [-37.15, 1.38] 30: b_coi_conditionHarrisproHarris:scaletopicZ b = -1.38 [-12.34, 10.15] 31: b_coi_scalevote_chance_1:scaletopicZ b = -12.20 [-37.92, -0.28] * 32: b_coi_conditionHarrisproHarris:scalevote_chance_1:scaletopicZ b = 10.67 [-2.80, 36.40] term result p_sig ```