dirty/quick analysis with frequentist mixed models (singular fits) ```r # weight on accuracy (singular frequentist lme4 mixed models) > m0 <- lmer(driftb1 ~ conditionEC * (platformZ + demrepZ) + (1 + conditionEC + demrepZ | study), data = d) term results 1: (Intercept) b = 0.32, SE = 0.10, t(3) = 3.12, p = .046, r = 0.86 2: conditionEC b = 0.20, SE = 0.05, t(4) = 3.76, p = .017, r = 0.87 3: platformZ b = 0.08, SE = 0.06, t(5) = 1.23, p = .275, r = 0.49 4: demrepZ b = −0.05, SE = 0.03, t(5) = −1.62, p = .172, r = 0.60 5: conditionEC:platformZ b = 0.01, SE = 0.05, t(5) = 0.23, p = .824, r = 0.10 6: conditionEC:demrepZ b = −0.02, SE = 0.03, t(1827) = −0.70, p = .486, r = 0.02 # boundary > m0 <- lmer(B ~ conditionEC * (platformZ + demrepZ) + (1 + conditionEC + demrepZ | study), data = d) term results 1: (Intercept) b = 3.04, SE = 0.17, t(5) = 17.89, p < .001, r = 0.99 2: conditionEC b = −0.06, SE = 0.07, t(23) = −0.90, p = .375, r = 0.18 3: platformZ b = −0.01, SE = 0.11, t(3) = −0.09, p = .936, r = 0.05 4: demrepZ b = 0.09, SE = 0.05, t(4) = 1.65, p = .170, r = 0.62 5: conditionEC:platformZ b = −0.07, SE = 0.07, t(104) = −1.09, p = .276, r = 0.11 6: conditionEC:demrepZ b = −0.08, SE = 0.06, t(313) = −1.20, p = .232, r = 0.07 # non-decision time > m0 <- lmer(nondectime ~ conditionEC * (platformZ + demrepZ) + (1 + conditionEC + demrepZ | study), data = d) term results 1: (Intercept) b = 3.13, SE = 0.23, t(4) = 13.82, p < .001, r = 0.99 2: conditionEC b = 0.12, SE = 0.07, t(6) = 1.78, p = .122, r = 0.57 3: platformZ b = 0.24, SE = 0.18, t(4) = 1.36, p = .256, r = 0.59 4: demrepZ b = −0.06, SE = 0.04, t(5) = −1.45, p = .210, r = 0.55 5: conditionEC:platformZ b = 0.05, SE = 0.07, t(10) = 0.76, p = .464, r = 0.23 6: conditionEC:demrepZ b = 0.01, SE = 0.06, t(483) = 0.22, p = .828, r = 0.01 # average drift (b0) > m0 <- lmer(driftb0 ~ conditionEC * (platformZ + demrepZ) + (1 + conditionEC + demrepZ | study), data = d) term results 1: (Intercept) b = −0.31, SE = 0.06, t(5) = −5.03, p = .005, r = 0.92 2: conditionEC b = −0.008, SE = 0.03, t(7) = −0.26, p = .802, r = 0.10 3: platformZ b = −0.12, SE = 0.04, t(3) = −3.26, p = .039, r = 0.87 4: demrepZ b = 0.05, SE = 0.03, t(6) = 1.73, p = .136, r = 0.59 5: conditionEC:platformZ b = 0.03, SE = 0.02, t(27) = 1.14, p = .263, r = 0.22 6: conditionEC:demrepZ b = −0.009, SE = 0.02, t(1606) = −0.38, p = .703, r = 0.01 # starting point > m0 <- lmer(x0 ~ conditionEC * (platformZ + demrepZ) + (1 + conditionEC + demrepZ | study), data = d) term results 1: (Intercept) b = −0.01, SE = 0.02, t(4) = −0.45, p = .675, r = 0.21 2: conditionEC b = −0.02, SE = 0.02, t(4) = −0.98, p = .387, r = 0.45 3: platformZ b = 0.01, SE = 0.01, t(16) = 1.13, p = .274, r = 0.28 4: demrepZ b = 0.03, SE = 0.02, t(5) = 1.51, p = .193, r = 0.56 5: conditionEC:platformZ b = −0.002, SE = 0.01, t(6) = −0.15, p = .889, r = 0.06 6: conditionEC:demrepZ b = −0.01, SE = 0.01, t(1827) = −0.93, p = .350, r = 0.02 ``` ![[1674496194.png]]