finalAnalyses

Set-Up

library(groundhog)
pkgs <-  c("lmerTest", "ggeffects","r2glmm", "tidyverse","here", "sjPlot", "ggpubr", "wesanderson")
groundhog.day <- '2022-07-25'
groundhog.library(pkgs, groundhog.day)
here::i_am("Analysis/finalConfAnalyses.qmd")
plotDir <- "/Volumes/Research Project/Metacognition/Study 1/Plots/"

Import Data

longDf <- as.data.frame( arrow::read_parquet(here("Data/confClean.parquet")) )

Scaling

longDf$outConfNeigh.Z <- scale(longDf$outConfNeigh)
longDf$inConfNeigh.Z <- scale(longDf$inConfNeigh)
longDf$allSelfNeigh.Z <- scale(longDf$allSelfNeigh)
longDf$eval.Z <- scale(longDf$eval)
longDf$outDegree.Z <- scale(longDf$outDegree)
longDf$inDegree.Z <- scale(longDf$inDegree)
longDf$evalBSWV.Z <- scale(longDf$evalBSWV)
longDf$evalBSWV.Z <- scale(longDf$evalBSWV)
longDf$evalBS.Z <- scale(longDf$evalBS)
longDf$devMid.Z <- scale(longDf$devMid)
longDf$devTS.Z <- scale(longDf$devTS)
longDf$confidence.Z <- scale(longDf$confidence)
longDf$NFC.Z <- scale(longDf$NFC)
longDf$SE.Z <- scale(longDf$SE)
longDf$SCC.Z <- scale(longDf$SCC)
longDf$DS.Z <- scale(longDf$DS)
longDf$CESD.Z <- scale(longDf$CESD)
longDf$MAIA.Z <- scale(longDf$MAIA)

Self-Uncertainty Modulates Trait Self-Certainty

m<-lmer(confidence.Z ~ COND + ( 1 | subID ) + ( COND | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

boundary (singular) fit: see help('isSingular')

r2beta(m)

  Effect   Rsq upper.CL lower.CL
1  Model 0.018    0.022    0.015
3 CONDSU 0.015    0.019    0.013
2 CONDNI 0.000    0.001    0.000

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Confidence", df.method = "satterthwaite",show.df=T)

	Confidence
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	0.097 (-0.045 – 0.238)	0.072	1.347	0.179	241.998
COND [NI]	-0.036 (-0.234 – 0.162)	0.100	-0.358	0.721	233.070
COND [SU]	-0.248 (-0.444 – -0.052)	0.099	-2.498	0.013	233.741
Random Effects
σ2	0.58
τ00 traits	0.03
τ00 subID	0.39
τ11 traits.CONDNI	0.00
τ11 traits.CONDSU	0.00
ρ01 traits.CONDNI	-0.11
ρ01 traits.CONDSU	0.04
N subID	236
N traits	296
Observations	34512
Marginal R2 / Conditional R2	0.021 / NA

Plot

m<-lmer(confidence ~ COND + ( 1 | subID ) + ( 1 | traits), data=longDf)
ggpredict(m, c("COND")) %>% plot()

Traits with More Implications Are Evaluated More Confidently

m<-lmer(confidence.Z ~ inDegree.Z + outDegree.Z + valence + ( valence + outDegree.Z + inDegree.Z | subID ) + ( 1 | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

boundary (singular) fit: see help('isSingular')

r2beta(m)

           Effect   Rsq upper.CL lower.CL
1           Model 0.010    0.013    0.008
3     outDegree.Z 0.005    0.007    0.004
4 valencepositive 0.005    0.007    0.003
2      inDegree.Z 0.000    0.000    0.000

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Confidence", df.method = "satterthwaite",show.df=T)

	Confidence
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.057 (-0.153 – 0.040)	0.049	-1.155	0.249	269.094
inDegree Z	-0.003 (-0.023 – 0.017)	0.010	-0.276	0.782	297.519
outDegree Z	0.061 (0.040 – 0.082)	0.010	5.844	<0.001	319.872
valence [positive]	0.115 (0.054 – 0.175)	0.031	3.720	<0.001	415.760
Random Effects
σ2	0.54
τ00 traits	0.02
τ00 subID	0.52
τ11 subID.valencepositive	0.13
τ11 subID.outDegree.Z	0.00
τ11 subID.inDegree.Z	0.00
ρ01 subID.valencepositive	-0.61
ρ01 subID.outDegree.Z	-0.43
ρ01 subID.inDegree.Z	0.13
N subID	236
N traits	296
Observations	34512
Marginal R2 / Conditional R2	0.012 / NA

Self-Certainty Reflects Self-Consistency

m<-lmer(confidence.Z ~ allSelfNeigh.Z*eval.Z + ( allSelfNeigh.Z + eval.Z  | subID ) + ( 1 | traits), data=longDf)
r2beta(m)

                 Effect   Rsq upper.CL lower.CL
1                 Model 0.097    0.104    0.090
4 allSelfNeigh.Z:eval.Z 0.047    0.052    0.042
3                eval.Z 0.040    0.045    0.035
2        allSelfNeigh.Z 0.000    0.000    0.000

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Confidence", df.method = "satterthwaite",show.df=T)

	Confidence
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.081 (-0.158 – -0.004)	0.039	-2.067	0.040	252.289
allSelfNeigh Z	-0.005 (-0.021 – 0.011)	0.008	-0.640	0.522	354.520
eval Z	0.192 (0.150 – 0.235)	0.022	8.929	<0.001	237.752
allSelfNeigh Z * eval Z	0.167 (0.158 – 0.176)	0.005	35.645	<0.001	25238.519
Random Effects
σ2	0.44
τ00 traits	0.01
τ00 subID	0.35
τ11 subID.allSelfNeigh.Z	0.00
τ11 subID.eval.Z	0.10
ρ01 subID.allSelfNeigh.Z	0.01
ρ01 subID.eval.Z	-0.62
ICC	0.52
N subID	236
N traits	296
Observations	34496
Marginal R2 / Conditional R2	0.065 / 0.548

m<-lmer(confidence ~ allSelfNeigh*eval + ( allSelfNeigh + eval  | subID ) + ( 1 | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

Plot

p <- ggpredict(m, c("allSelfNeigh","eval[1,4,7]"))
ConsistencyConfidencePlot <-ggplot(p, aes(x, predicted)) +  geom_line(aes(linetype=group, color=group)) + geom_ribbon(aes(ymin=conf.low, ymax=conf.high, fill=group), alpha=0.15) + scale_linetype_discrete(labels = c("Low","Medium","High")) + scale_color_manual(labels = c("Low","Medium","High"), values = wes_palette("Darjeeling1")) + scale_fill_manual( 
                      labels=c("Low","Medium","High"), values = wes_palette("Darjeeling1")) + theme(
    legend.position = c(.2, .7),
    legend.justification = c("left", "bottom"),
    legend.box.just = "left",
    legend.margin = margin(6, 6, 6, 6)
    ) + theme(axis.text=element_text(size=12),
        axis.title=element_text(size=12,face="bold")) + theme(legend.text = element_text(size=12)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black")) +
  xlab("Neighboring Self-Evaluations") + ylab("Confidence")
ConsistencyConfidencePlot

ggsave(paste0(plotDir,"ConsistConf",".png"), width = 9, height = 6, dpi=500, units="in")

Warning in dir.create(dir, recursive = TRUE): cannot create dir '/Volumes/
Research Project', reason 'Permission denied'

Warning in normalizePath(dir): path[1]="/Volumes/Research Project/Metacognition/
Study 1/Plots": No such file or directory

Warning in grDevices::dev.off(): agg could not write to the given file

ggsave(paste0(plotDir,"ConsistConf",".tiff"), width = 9, height = 6, dpi=500, units="in")

Warning in dir.create(dir, recursive = TRUE): cannot create dir '/Volumes/
Research Project', reason 'Permission denied'

Warning in normalizePath(dir): path[1]="/Volumes/Research Project/Metacognition/
Study 1/Plots": No such file or directory

Warning in grDevices::dev.off(): agg could not write to the given file

Self-Certainty Spreads Among Related Traits

m<-lmer(inConfNeigh.Z ~ confidence.Z + (  confidence.Z | subID ) + ( 1 | traits), data=longDf)
r2beta(m)

        Effect   Rsq upper.CL lower.CL
1        Model 0.008     0.01    0.006
2 confidence.Z 0.008     0.01    0.006

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Inwards Confidence", df.method = "satterthwaite",show.df=T)

	Inwards Confidence
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	0.044 (-0.058 – 0.146)	0.052	0.847	0.398	238.779
confidence Z	0.064 (0.045 – 0.083)	0.010	6.530	<0.001	270.199
Random Effects
σ2	0.20
τ00 traits	0.01
τ00 subID	0.62
τ11 subID.confidence.Z	0.02
ρ01 subID	-0.41
ICC	0.76
N subID	236
N traits	296
Observations	34442
Marginal R2 / Conditional R2	0.005 / 0.764

m<-lmer(outConfNeigh.Z ~ confidence.Z + (  confidence.Z | subID ) + ( 1 | traits), data=longDf)
r2beta(m)

        Effect   Rsq upper.CL lower.CL
1        Model 0.005    0.007    0.004
2 confidence.Z 0.005    0.007    0.004

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Outwards Confidence", df.method = "satterthwaite",show.df=T)

	Outwards Confidence
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	0.041 (-0.067 – 0.149)	0.055	0.753	0.452	237.659
confidence Z	0.052 (0.033 – 0.070)	0.009	5.480	<0.001	262.902
Random Effects
σ2	0.13
τ00 traits	0.01
τ00 subID	0.70
τ11 subID.confidence.Z	0.02
ρ01 subID	-0.37
ICC	0.85
N subID	236
N traits	296
Observations	34511
Marginal R2 / Conditional R2	0.003 / 0.846

Greater Confidence Predicts More Extreme Self-Evaluations

Deviation from Midpoint

m<-lmer( devMid.Z ~ confidence.Z + ( confidence.Z | subID ) + ( 1 | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
summary(m)

Linear mixed model fit by REML. t-tests use Satterthwaite's method [
lmerModLmerTest]
Formula: devMid.Z ~ confidence.Z + (confidence.Z | subID) + (1 | traits)
   Data: longDf
Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 2e+05))

REML criterion at convergence: 86965.1

Scaled residuals: 
    Min      1Q  Median      3Q     Max 
-3.5005 -0.6960  0.0281  0.7189  4.3999 

Random effects:
 Groups   Name         Variance Std.Dev. Corr
 traits   (Intercept)  0.04549  0.2133       
 subID    (Intercept)  0.08539  0.2922       
          confidence.Z 0.09150  0.3025   0.07
 Residual              0.68965  0.8304       
Number of obs: 34497, groups:  traits, 296; subID, 236

Fixed effects:
              Estimate Std. Error        df t value Pr(>|t|)    
(Intercept)   -0.06598    0.02362 377.35505  -2.793  0.00549 ** 
confidence.Z   0.46929    0.02123 231.59350  22.108  < 2e-16 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Correlation of Fixed Effects:
            (Intr)
confidenc.Z 0.027 

r2beta(m)

        Effect   Rsq upper.CL lower.CL
1        Model 0.269    0.278     0.26
2 confidence.Z 0.269    0.278     0.26

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Deviation", df.method = "satterthwaite",show.df=T)

	Deviation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.066 (-0.112 – -0.020)	0.024	-2.793	0.005	377.355
confidence Z	0.469 (0.427 – 0.511)	0.021	22.108	<0.001	231.594
Random Effects
σ2	0.69
τ00 traits	0.05
τ00 subID	0.09
τ11 subID.confidence.Z	0.09
ρ01 subID	0.07
ICC	0.24
N subID	236
N traits	296
Observations	34497
Marginal R2 / Conditional R2	0.194 / 0.391

Self-Evaluations by Valence

m<-lmer( eval.Z ~ confidence.Z * valence + ( confidence.Z + valence | subID ) + ( 1 | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
r2beta(m)

                        Effect   Rsq upper.CL lower.CL
1                        Model 0.306    0.315    0.297
3              valencepositive 0.253    0.262    0.244
4 confidence.Z:valencepositive 0.042    0.047    0.037
2                 confidence.Z 0.000    0.001    0.000

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Deviation", df.method = "satterthwaite",show.df=T)

	Deviation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.364 (-0.437 – -0.290)	0.038	-9.664	<0.001	500.816
confidence Z	0.012 (-0.018 – 0.042)	0.015	0.782	0.435	307.796
valence [positive]	0.801 (0.705 – 0.897)	0.049	16.404	<0.001	495.930
confidence Z * valence [positive]	0.289 (0.269 – 0.309)	0.010	27.873	<0.001	27978.414
Random Effects
σ2	0.51
τ00 traits	0.11
τ00 subID	0.15
τ11 subID.confidence.Z	0.04
τ11 subID.valencepositive	0.21
ρ01 subID.confidence.Z	0.49
ρ01 subID.valencepositive	-0.74
ICC	0.35
N subID	236
N traits	296
Observations	34497
Marginal R2 / Conditional R2	0.211 / 0.486

m<-lmer( eval ~ confidence * valence + ( confidence + valence | subID ) + ( 1 | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

p <- ggpredict(m, c("confidence","valence"))
ValenceDeviatePlot <-ggplot(p, aes(x, predicted)) +  geom_line(aes(linetype=group, color=group)) + geom_ribbon(aes(ymin=conf.low, ymax=conf.high, fill=group), alpha=0.15) + scale_linetype_discrete(labels = c("Negative","Positive")) + scale_color_manual(labels = c("Negative","Positive"), values = wes_palette("Darjeeling1")) + scale_fill_manual( 
                      labels=c("Negative","Positive"), values = wes_palette("Darjeeling1")) + theme(
    legend.position = c(.2, .7),
    legend.justification = c("left", "bottom"),
    legend.box.just = "left",
    legend.margin = margin(6, 6, 6, 6)
    ) + theme(axis.text=element_text(size=12),
        axis.title=element_text(size=12,face="bold")) + theme(legend.text = element_text(size=12)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black")) +
  xlab("Confidence") + ylab("SelfEvaluation") + scale_y_continuous(breaks=seq(1,7,1))
ValenceDeviatePlot

Deviation from Composite of Average Evaluation Per Trait and Per Subject

m<-lmer(devTS.Z ~ confidence.Z + ( confidence.Z | subID ) + ( 1 | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
summary(m)

Linear mixed model fit by REML. t-tests use Satterthwaite's method [
lmerModLmerTest]
Formula: devTS.Z ~ confidence.Z + (confidence.Z | subID) + (1 | traits)
   Data: longDf
Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 2e+05))

REML criterion at convergence: 92226.9

Scaled residuals: 
    Min      1Q  Median      3Q     Max 
-2.8961 -0.7173 -0.1102  0.6093  4.7691 

Random effects:
 Groups   Name         Variance Std.Dev. Corr
 traits   (Intercept)  0.03653  0.1911       
 subID    (Intercept)  0.08086  0.2844       
          confidence.Z 0.04271  0.2067   0.20
 Residual              0.81081  0.9004       
Number of obs: 34497, groups:  traits, 296; subID, 236

Fixed effects:
              Estimate Std. Error        df t value Pr(>|t|)    
(Intercept)   -0.02504    0.02254 364.23761  -1.111    0.267    
confidence.Z   0.29640    0.01559 224.13131  19.013   <2e-16 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Correlation of Fixed Effects:
            (Intr)
confidenc.Z 0.108 

r2beta(m)

        Effect   Rsq upper.CL lower.CL
1        Model 0.119    0.127    0.112
2 confidence.Z 0.119    0.127    0.112

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Deviation", df.method = "satterthwaite",show.df=T)

	Deviation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.025 (-0.069 – 0.019)	0.023	-1.111	0.267	364.238
confidence Z	0.296 (0.266 – 0.327)	0.016	19.013	<0.001	224.131
Random Effects
σ2	0.81
τ00 traits	0.04
τ00 subID	0.08
τ11 subID.confidence.Z	0.04
ρ01 subID	0.20
ICC	0.16
N subID	236
N traits	296
Observations	34497
Marginal R2 / Conditional R2	0.083 / 0.234

Controlling for Average Evaluation Per Trait and Per Subject

{m<-lmer(scale(eval) ~ scale(confidence) + scale(evalBSWV) + scale(evalBT) + ( scale(confidence) | subID ) + ( 1 | traits), data=longDf)} summary(m) r2glmm::r2beta(m)

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.025 (-0.069 – 0.019)	0.023	-1.111	0.267	364.238
confidence Z	0.296 (0.266 – 0.327)	0.016	19.013	<0.001	224.131
Random Effects
σ2	0.81
τ00 traits	0.04
τ00 subID	0.08
τ11 subID.confidence.Z	0.04
ρ01 subID	0.20
ICC	0.16
N subID	236
N traits	296
Observations	34497
Marginal R2 / Conditional R2	0.083 / 0.234

Individual Differences in Self-Certainty: Main Effects

Self-Concept Clarity

m<-lmer( confidence.Z ~ SCC.Z + ( 1 | subID ) + ( SCC.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
r2beta(m)

  Effect   Rsq upper.CL lower.CL
1  Model 0.013    0.016     0.01
2  SCC.Z 0.013    0.016     0.01

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.000 (-0.083 – 0.082)	0.042	-0.009	0.993	262.499
SCC Z	0.092 (0.011 – 0.172)	0.041	2.239	0.026	235.470
Random Effects
σ2	0.57
τ00 traits	0.03
τ00 subID	0.39
τ11 traits.SCC.Z	0.00
ρ01 traits	-0.13
ICC	0.42
N subID	236
N traits	296
Observations	34512
Marginal R2 / Conditional R2	0.008 / 0.427

Need for Cognition

m<-lmer( confidence.Z ~ NFC.Z + ( 1 | subID ) + ( NFC.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

boundary (singular) fit: see help('isSingular')

r2beta(m)

  Effect   Rsq upper.CL lower.CL
1  Model 0.003    0.004    0.002
2  NFC.Z 0.003    0.004    0.002

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.004 (-0.088 – 0.080)	0.043	-0.090	0.928	258.568
NFC Z	0.043 (-0.038 – 0.125)	0.041	1.049	0.295	231.046
Random Effects
σ2	0.58
τ00 traits	0.03
τ00 subID	0.40
τ11 traits.NFC.Z	0.00
ρ01 traits	1.00
N subID	233
N traits	296
Observations	34069
Marginal R2 / Conditional R2	0.003 / NA

Self-Esteem

m<-lmer( confidence.Z ~ SE.Z + ( 1 | subID ) + ( SE.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
r2beta(m)

  Effect   Rsq upper.CL lower.CL
1  Model 0.014    0.018    0.011
2   SE.Z 0.014    0.018    0.011

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.002 (-0.086 – 0.081)	0.042	-0.055	0.956	260.111
SE Z	0.098 (0.017 – 0.179)	0.041	2.378	0.018	233.358
Random Effects
σ2	0.57
τ00 traits	0.03
τ00 subID	0.39
τ11 traits.SE.Z	0.00
ρ01 traits	-0.03
ICC	0.42
N subID	234
N traits	296
Observations	34220
Marginal R2 / Conditional R2	0.010 / 0.429

Dialectical Self-Views

m<-lmer( confidence.Z ~ DS.Z + ( 1 | subID ) + ( DS.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
r2beta(m)

  Effect   Rsq upper.CL lower.CL
1  Model 0.009    0.011    0.007
2   DS.Z 0.009    0.011    0.007

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	0.003 (-0.081 – 0.086)	0.042	0.069	0.945	260.051
DS Z	-0.076 (-0.157 – 0.005)	0.041	-1.846	0.066	233.382
Random Effects
σ2	0.57
τ00 traits	0.03
τ00 subID	0.39
τ11 traits.DS.Z	0.00
ρ01 traits	0.04
ICC	0.43
N subID	234
N traits	296
Observations	34215
Marginal R2 / Conditional R2	0.006 / 0.429

Interoceptive Awareness

m<-lmer( confidence.Z ~ MAIA.Z + ( 1 | subID ) + ( MAIA.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
r2beta(m)

  Effect   Rsq upper.CL lower.CL
1  Model 0.028    0.032    0.024
2 MAIA.Z 0.028    0.032    0.024

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.000 (-0.082 – 0.082)	0.041	-0.002	0.998	263.317
MAIA Z	0.137 (0.057 – 0.216)	0.040	3.396	0.001	235.025
Random Effects
σ2	0.58
τ00 traits	0.03
τ00 subID	0.38
τ11 traits.MAIA.Z	0.00
ρ01 traits	-0.17
ICC	0.42
N subID	236
N traits	296
Observations	34512
Marginal R2 / Conditional R2	0.019 / 0.426

Depressive Symptoms

m<-lmer( confidence.Z ~ CESD.Z + ( 1 | subID ) + ( CESD.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
r2beta(m)

  Effect   Rsq upper.CL lower.CL
1  Model 0.001    0.003    0.001
2 CESD.Z 0.001    0.003    0.001

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.006 (-0.090 – 0.078)	0.042	-0.140	0.888	259.812
CESD Z	-0.032 (-0.113 – 0.050)	0.041	-0.763	0.446	232.808
Random Effects
σ2	0.58
τ00 traits	0.03
τ00 subID	0.39
τ11 traits.CESD.Z	0.00
ρ01 traits	-0.12
ICC	0.42
N subID	234
N traits	296
Observations	34217
Marginal R2 / Conditional R2	0.001 / 0.424

Individual Differences in Self-Certainty as a Function of Outdegree

Self-Concept Clarity

m<-lmer( confidence.Z ~ SCC.Z*outDegree.Z + ( outDegree.Z | subID ) + ( SCC.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
rb <- r2beta(m)
data.frame(rb$Effect,rb$Rsq)

          rb.Effect       rb.Rsq
1             Model 0.0176990026
2             SCC.Z 0.0125579637
3       outDegree.Z 0.0049911976
4 SCC.Z:outDegree.Z 0.0001239061

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.000 (-0.083 – 0.082)	0.042	-0.012	0.991	259.492
SCC Z	0.091 (0.011 – 0.172)	0.041	2.237	0.026	235.399
outDegree Z	0.057 (0.036 – 0.078)	0.011	5.371	<0.001	310.938
SCC Z * outDegree Z	0.009 (-0.001 – 0.019)	0.005	1.699	0.091	199.872
Random Effects
σ2	0.57
τ00 traits	0.03
τ00 subID	0.39
τ11 traits.SCC.Z	0.00
τ11 subID.outDegree.Z	0.00
ρ01 traits	-0.23
ρ01 subID	-0.33
ICC	0.42
N subID	236
N traits	296
Observations	34512
Marginal R2 / Conditional R2	0.012 / 0.429

Plot

m<-lmer( confidence ~ SCC*outDegree + ( outDegree | subID ) + ( SCC | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, : Model is nearly unidentifiable: very large eigenvalue
 - Rescale variables?

p <- ggpredict(m, c("SCC","outDegree"))
SCC.outdeg.Conf.Plot <-ggplot(p, aes(x, predicted)) +  geom_line(aes(linetype=group, color=group)) + geom_ribbon(aes(ymin=conf.low, ymax=conf.high, fill=group), alpha=0.15) + scale_linetype_discrete(labels = c("Low Outdegree","Medium Outdegree","High Outdegree")) + scale_color_manual(labels = c("Low Outdegree","Medium Outdegree","High Outdegree"), values = wes_palette("Darjeeling1")) + scale_fill_manual( 
                      labels=c("Low Outdegree","Medium Outdegree","High Outdegree"), values = wes_palette("Darjeeling1")) + theme(
    legend.position = c(.2, .7),
    legend.justification = c("left", "bottom"),
    legend.box.just = "left",
    legend.margin = margin(6, 6, 6, 6)
    ) + theme(axis.text=element_text(size=12),
        axis.title=element_text(size=12,face="bold")) + theme(legend.text = element_text(size=12)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black")) +
  xlab("Self-Concept Clarity") + ylab("Confidence")
SCC.outdeg.Conf.Plot

Need for Cognition

m<-lmer( confidence.Z ~ NFC.Z*outDegree.Z + ( outDegree.Z | subID ) + ( NFC.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

boundary (singular) fit: see help('isSingular')

rb <- r2beta(m)
data.frame(rb$Effect,rb$Rsq)

          rb.Effect       rb.Rsq
1             Model 0.0080124327
2       outDegree.Z 0.0050688725
3             NFC.Z 0.0028302428
4 NFC.Z:outDegree.Z 0.0001221301

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.004 (-0.088 – 0.080)	0.043	-0.093	0.926	255.641
NFC Z	0.043 (-0.038 – 0.125)	0.041	1.046	0.296	231.020
outDegree Z	0.058 (0.037 – 0.079)	0.011	5.396	<0.001	310.428
NFC Z * outDegree Z	0.009 (-0.001 – 0.018)	0.005	1.846	0.066	220.168
Random Effects
σ2	0.58
τ00 traits	0.03
τ00 subID	0.40
τ11 traits.NFC.Z	0.00
τ11 subID.outDegree.Z	0.00
ρ01 traits	1.00
ρ01 subID	-0.32
N subID	233
N traits	296
Observations	34069
Marginal R2 / Conditional R2	0.009 / NA

Plot

m<-lmer( confidence ~ NFC*outDegree + ( outDegree | subID ) + ( NFC | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

boundary (singular) fit: see help('isSingular')

p <- ggpredict(m, c("NFC","outDegree"))
NFC.outdeg.Conf.Plot <-ggplot(p, aes(x, predicted)) +  geom_line(aes(linetype=group, color=group)) + geom_ribbon(aes(ymin=conf.low, ymax=conf.high, fill=group), alpha=0.15) + scale_linetype_discrete(labels = c("Low Outdegree","Medium Outdegree","High Outdegree")) + scale_color_manual(labels = c("Low Outdegree","Medium Outdegree","High Outdegree"), values = wes_palette("Darjeeling1")) + scale_fill_manual( 
                      labels=c("Low Outdegree","Medium Outdegree","High Outdegree"), values = wes_palette("Darjeeling1")) + theme(
    legend.position = c(.2, .7),
    legend.justification = c("left", "bottom"),
    legend.box.just = "left",
    legend.margin = margin(6, 6, 6, 6)
    ) + theme(axis.text=element_text(size=12),
        axis.title=element_text(size=12,face="bold")) + theme(legend.text = element_text(size=12)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black")) +
  xlab("Need for Cognition") + ylab("Confidence")
NFC.outdeg.Conf.Plot

Self-Esteem

m<-lmer( confidence.Z ~ SE.Z*outDegree.Z + ( outDegree.Z | subID ) + ( SE.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
rb <- r2beta(m)
data.frame(rb$Effect,rb$Rsq)

         rb.Effect       rb.Rsq
1            Model 1.964172e-02
2             SE.Z 1.435068e-02
3      outDegree.Z 5.211827e-03
4 SE.Z:outDegree.Z 9.620607e-05

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.002 (-0.085 – 0.080)	0.042	-0.058	0.954	257.059
SE Z	0.098 (0.017 – 0.179)	0.041	2.376	0.018	233.324
outDegree Z	0.059 (0.037 – 0.080)	0.011	5.474	<0.001	308.942
SE Z * outDegree Z	0.008 (-0.002 – 0.018)	0.005	1.507	0.134	194.228
Random Effects
σ2	0.57
τ00 traits	0.03
τ00 subID	0.39
τ11 traits.SE.Z	0.00
τ11 subID.outDegree.Z	0.00
ρ01 traits	-0.11
ρ01 subID	-0.33
ICC	0.42
N subID	234
N traits	296
Observations	34220
Marginal R2 / Conditional R2	0.013 / 0.431

Plot

m<-lmer( confidence ~ SE*outDegree + ( outDegree | subID ) + ( SE | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, :
Model failed to converge with max|grad| = 0.00715132 (tol = 0.002, component 1)

Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, : Model is nearly unidentifiable: very large eigenvalue
 - Rescale variables?

p <- ggpredict(m, c("SE","outDegree"))
SE.outdeg.Conf.Plot <-ggplot(p, aes(x, predicted)) +  geom_line(aes(linetype=group, color=group)) + geom_ribbon(aes(ymin=conf.low, ymax=conf.high, fill=group), alpha=0.15) + scale_linetype_discrete(labels = c("Low Outdegree","Medium Outdegree","High Outdegree")) + scale_color_manual(labels = c("Low Outdegree","Medium Outdegree","High Outdegree"), values = wes_palette("Darjeeling1")) + scale_fill_manual( 
                      labels=c("Low Outdegree","Medium Outdegree","High Outdegree"), values = wes_palette("Darjeeling1")) + theme(
    legend.position = c(.2, .7),
    legend.justification = c("left", "bottom"),
    legend.box.just = "left",
    legend.margin = margin(6, 6, 6, 6)
    ) + theme(axis.text=element_text(size=12),
        axis.title=element_text(size=12,face="bold")) + theme(legend.text = element_text(size=12)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black")) +
  xlab("Need for Cognition") + ylab("Confidence")
SE.outdeg.Conf.Plot

Dialectical Self-Views

m<-lmer( confidence.Z ~ DS.Z*outDegree.Z + ( outDegree.Z | subID ) + ( DS.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
r2beta(m)

            Effect   Rsq upper.CL lower.CL
1            Model 0.014    0.017    0.011
2             DS.Z 0.009    0.011    0.006
3      outDegree.Z 0.005    0.007    0.003
4 DS.Z:outDegree.Z 0.000    0.000    0.000

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	0.003 (-0.080 – 0.086)	0.042	0.067	0.947	257.114
DS Z	-0.076 (-0.157 – 0.005)	0.041	-1.842	0.067	233.382
outDegree Z	0.058 (0.036 – 0.079)	0.011	5.341	<0.001	312.694
DS Z * outDegree Z	-0.006 (-0.017 – 0.004)	0.005	-1.134	0.258	201.960
Random Effects
σ2	0.57
τ00 traits	0.03
τ00 subID	0.39
τ11 traits.DS.Z	0.00
τ11 subID.outDegree.Z	0.00
ρ01 traits	0.10
ρ01 subID	-0.31
ICC	0.43
N subID	234
N traits	296
Observations	34215
Marginal R2 / Conditional R2	0.009 / 0.431

Plot

m<-lmer( confidence ~ DS*outDegree + ( outDegree | subID ) + ( DS | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, : Model is nearly unidentifiable: very large eigenvalue
 - Rescale variables?

p <- ggpredict(m, c("DS","outDegree"))
DS.outdeg.Conf.Plot <-ggplot(p, aes(x, predicted)) +  geom_line(aes(linetype=group, color=group)) + geom_ribbon(aes(ymin=conf.low, ymax=conf.high, fill=group), alpha=0.15) + scale_linetype_discrete(labels = c("Low Outdegree","Medium Outdegree","High Outdegree")) + scale_color_manual(labels = c("Low Outdegree","Medium Outdegree","High Outdegree"), values = wes_palette("Darjeeling1")) + scale_fill_manual( 
                      labels=c("Low Outdegree","Medium Outdegree","High Outdegree"), values = wes_palette("Darjeeling1")) + theme(
    legend.position = c(.2, .7),
    legend.justification = c("left", "bottom"),
    legend.box.just = "left",
    legend.margin = margin(6, 6, 6, 6)
    ) + theme(axis.text=element_text(size=12),
        axis.title=element_text(size=12,face="bold")) + theme(legend.text = element_text(size=12)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black")) +
  xlab("Outdegree Centrality") + ylab("Confidence")
DS.outdeg.Conf.Plot

Interoceptive Awareness

m<-lmer( confidence.Z ~ MAIA.Z*outDegree.Z + ( outDegree.Z | subID ) + ( MAIA.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
r2beta(m)

              Effect   Rsq upper.CL lower.CL
1              Model 0.033    0.037    0.028
2             MAIA.Z 0.028    0.032    0.024
3        outDegree.Z 0.005    0.007    0.003
4 MAIA.Z:outDegree.Z 0.000    0.000    0.000

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.000 (-0.082 – 0.081)	0.041	-0.003	0.997	260.222
MAIA Z	0.137 (0.057 – 0.216)	0.040	3.398	0.001	235.009
outDegree Z	0.058 (0.036 – 0.079)	0.011	5.374	<0.001	311.873
MAIA Z * outDegree Z	0.003 (-0.008 – 0.013)	0.005	0.506	0.614	187.430
Random Effects
σ2	0.57
τ00 traits	0.03
τ00 subID	0.38
τ11 traits.MAIA.Z	0.00
τ11 subID.outDegree.Z	0.00
ρ01 traits	-0.21
ρ01 subID	-0.31
ICC	0.42
N subID	236
N traits	296
Observations	34512
Marginal R2 / Conditional R2	0.022 / 0.428

Plot

m<-lmer( confidence ~ MAIA*outDegree + ( outDegree | subID ) + ( MAIA | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, :
Model failed to converge with max|grad| = 0.0119347 (tol = 0.002, component 1)

Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, : Model is nearly unidentifiable: very large eigenvalue
 - Rescale variables?

p <- ggpredict(m, c("MAIA","outDegree"))
MAIA.outdeg.Conf.Plot <-ggplot(p, aes(x, predicted)) +  geom_line(aes(linetype=group, color=group)) + geom_ribbon(aes(ymin=conf.low, ymax=conf.high, fill=group), alpha=0.15) + scale_linetype_discrete(labels = c("Low Outdegree","Medium Outdegree","High Outdegree")) + scale_color_manual(labels = c("Low Outdegree","Medium Outdegree","High Outdegree"), values = wes_palette("Darjeeling1")) + scale_fill_manual( 
                      labels=c("Low Outdegree","Medium Outdegree","High Outdegree"), values = wes_palette("Darjeeling1")) + theme(
    legend.position = c(.2, .7),
    legend.justification = c("left", "bottom"),
    legend.box.just = "left",
    legend.margin = margin(6, 6, 6, 6)
    ) + theme(axis.text=element_text(size=12),
        axis.title=element_text(size=12,face="bold")) + theme(legend.text = element_text(size=12)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black")) +
  xlab("Outdegree Centrality") + ylab("Confidence")
MAIA.outdeg.Conf.Plot

Depressive Symptoms

m<-lmer( confidence.Z ~ CESD.Z*outDegree.Z + ( outDegree.Z | subID ) + ( CESD.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
r2beta(m)

              Effect   Rsq upper.CL lower.CL
1              Model 0.007    0.009    0.005
3        outDegree.Z 0.005    0.007    0.003
2             CESD.Z 0.001    0.003    0.001
4 CESD.Z:outDegree.Z 0.000    0.001    0.000

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.006 (-0.090 – 0.077)	0.042	-0.144	0.886	256.865
CESD Z	-0.031 (-0.113 – 0.050)	0.041	-0.761	0.447	232.742
outDegree Z	0.058 (0.037 – 0.079)	0.011	5.392	<0.001	310.358
CESD Z * outDegree Z	-0.011 (-0.021 – -0.000)	0.005	-2.054	0.041	183.004
Random Effects
σ2	0.58
τ00 traits	0.03
τ00 subID	0.39
τ11 traits.CESD.Z	0.00
τ11 subID.outDegree.Z	0.00
ρ01 traits	0.00
ρ01 subID	-0.31
ICC	0.42
N subID	234
N traits	296
Observations	34217
Marginal R2 / Conditional R2	0.004 / 0.426

Plot

m<-lmer( confidence ~ CESD*outDegree + ( outDegree | subID ) + ( CESD | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, :
Model failed to converge with max|grad| = 0.0166039 (tol = 0.002, component 1)

Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, : Model is nearly unidentifiable: very large eigenvalue
 - Rescale variables?

p <- ggpredict(m, c("CESD","outDegree"))
CESD.outdeg.Conf.Plot <-ggplot(p, aes(x, predicted)) +  geom_line(aes(linetype=group, color=group)) + geom_ribbon(aes(ymin=conf.low, ymax=conf.high, fill=group), alpha=0.15) + scale_linetype_discrete(labels = c("Low Outdegree","Medium Outdegree","High Outdegree")) + scale_color_manual(labels = c("Low Outdegree","Medium Outdegree","High Outdegree"), values = wes_palette("Darjeeling1")) + scale_fill_manual( 
                      labels=c("Low Outdegree","Medium Outdegree","High Outdegree"), values = wes_palette("Darjeeling1")) + theme(
    legend.position = c(.2, .7),
    legend.justification = c("left", "bottom"),
    legend.box.just = "left",
    legend.margin = margin(6, 6, 6, 6)
    ) + theme(axis.text=element_text(size=12),
        axis.title=element_text(size=12,face="bold")) + theme(legend.text = element_text(size=12)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black")) +
  xlab("Outdegree Centrality") + ylab("Confidence")
CESD.outdeg.Conf.Plot

Individual Differences in Self-Certainty as a Function of Valence

Self-Concept Clarity

m<-lmer( confidence.Z ~ SCC.Z*valence + ( valence | subID ) + ( SCC.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
rb <- r2beta(m)
data.frame(rb$Effect,rb$Rsq)

              rb.Effect      rb.Rsq
1                 Model 0.018400383
2       valencepositive 0.004527729
3                 SCC.Z 0.003140197
4 SCC.Z:valencepositive 0.001174888

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.054 (-0.150 – 0.043)	0.049	-1.094	0.275	272.858
SCC Z	0.064 (-0.029 – 0.157)	0.047	1.358	0.176	235.096
valence [positive]	0.109 (0.047 – 0.170)	0.031	3.481	0.001	432.168
SCC Z * valence [positive]	0.055 (0.006 – 0.104)	0.025	2.227	0.027	239.705
Random Effects
σ2	0.54
τ00 traits	0.03
τ00 subID	0.52
τ11 traits.SCC.Z	0.00
τ11 subID.valencepositive	0.13
ρ01 traits	-0.54
ρ01 subID	-0.63
ICC	0.45
N subID	236
N traits	296
Observations	34512
Marginal R2 / Conditional R2	0.012 / 0.458

Plot

m<-lmer( confidence ~ SCC*valence + ( valence | subID ) + ( SCC | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

p <- ggpredict(m, c("SCC","valence"))
SCC.outdeg.Conf.Plot <-ggplot(p, aes(x, predicted)) +  geom_line(aes(linetype=group, color=group)) + geom_ribbon(aes(ymin=conf.low, ymax=conf.high, fill=group), alpha=0.15) + scale_linetype_discrete(labels = c("Negative", "Positive")) + scale_color_manual(labels = c("Negative", "Positive"), values = wes_palette("Darjeeling1")) + scale_fill_manual( 
                      labels=c("Negative", "Positive"), values = wes_palette("Darjeeling1")) + theme(
    legend.position = c(.2, .7),
    legend.justification = c("left", "bottom"),
    legend.box.just = "left",
    legend.margin = margin(6, 6, 6, 6)
    ) + theme(axis.text=element_text(size=12),
        axis.title=element_text(size=12,face="bold")) + theme(legend.text = element_text(size=12)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black")) +
  xlab("Self-Concept Clarity") + ylab("Confidence")
SCC.outdeg.Conf.Plot

Need for Cognition

m<-lmer( confidence.Z ~ NFC.Z*valence + ( valence | subID ) + ( NFC.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

boundary (singular) fit: see help('isSingular')

rb <- r2beta(m)
data.frame(rb$Effect,rb$Rsq)

              rb.Effect       rb.Rsq
1                 Model 0.0078669202
2       valencepositive 0.0046557854
3                 NFC.Z 0.0005587740
4 NFC.Z:valencepositive 0.0003868185

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.058 (-0.156 – 0.040)	0.050	-1.171	0.243	268.786
NFC Z	0.027 (-0.067 – 0.121)	0.048	0.569	0.570	231.054
valence [positive]	0.111 (0.048 – 0.173)	0.032	3.494	0.001	425.458
NFC Z * valence [positive]	0.032 (-0.018 – 0.081)	0.025	1.271	0.205	231.205
Random Effects
σ2	0.55
τ00 traits	0.03
τ00 subID	0.52
τ11 traits.NFC.Z	0.00
τ11 subID.valencepositive	0.13
ρ01 traits	1.00
ρ01 subID	-0.62
N subID	233
N traits	296
Observations	34069
Marginal R2 / Conditional R2	0.009 / NA

Plot

m<-lmer( confidence ~ NFC*valence + ( valence | subID ) + ( NFC | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

boundary (singular) fit: see help('isSingular')

p <- ggpredict(m, c("NFC","valence"))
NFC.outdeg.Conf.Plot <-ggplot(p, aes(x, predicted)) +  geom_line(aes(linetype=group, color=group)) + geom_ribbon(aes(ymin=conf.low, ymax=conf.high, fill=group), alpha=0.15) + scale_linetype_discrete(labels = c("Negative", "Positive")) + scale_color_manual(labels = c("Negative", "Positive"), values = wes_palette("Darjeeling1")) + scale_fill_manual( 
                      labels=c("Negative", "Positive"), values = wes_palette("Darjeeling1")) + theme(
    legend.position = c(.2, .7),
    legend.justification = c("left", "bottom"),
    legend.box.just = "left",
    legend.margin = margin(6, 6, 6, 6)
    ) + theme(axis.text=element_text(size=12),
        axis.title=element_text(size=12,face="bold")) + theme(legend.text = element_text(size=12)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black")) +
  xlab("Need for Cognition") + ylab("Confidence")
NFC.outdeg.Conf.Plot

Self-Esteem

m<-lmer( confidence.Z ~ SE.Z*valence + ( valence | subID ) + ( SE.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
rb <- r2beta(m)
data.frame(rb$Effect,rb$Rsq)

             rb.Effect      rb.Rsq
1                Model 0.020521418
2      valencepositive 0.004670059
3                 SE.Z 0.003448402
4 SE.Z:valencepositive 0.001435040

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.056 (-0.154 – 0.041)	0.049	-1.141	0.255	270.204
SE Z	0.067 (-0.026 – 0.161)	0.048	1.416	0.158	232.911
valence [positive]	0.110 (0.049 – 0.172)	0.031	3.512	<0.001	429.216
SE Z * valence [positive]	0.061 (0.012 – 0.110)	0.025	2.450	0.015	235.976
Random Effects
σ2	0.54
τ00 traits	0.03
τ00 subID	0.52
τ11 traits.SE.Z	0.00
τ11 subID.valencepositive	0.13
ρ01 traits	-0.47
ρ01 subID	-0.64
ICC	0.45
N subID	234
N traits	296
Observations	34220
Marginal R2 / Conditional R2	0.014 / 0.460

Plot

m<-lmer( confidence ~ SE*valence + ( valence | subID ) + ( SE | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

p <- ggpredict(m, c("SE","valence"))
SE.outdeg.Conf.Plot <-ggplot(p, aes(x, predicted)) +  geom_line(aes(linetype=group, color=group)) + geom_ribbon(aes(ymin=conf.low, ymax=conf.high, fill=group), alpha=0.15) + scale_linetype_discrete(labels = c("Negative", "Positive")) + scale_color_manual(labels = c("Negative", "Positive"), values = wes_palette("Darjeeling1")) + scale_fill_manual( 
                      labels=c("Negative", "Positive"), values = wes_palette("Darjeeling1")) + theme(
    legend.position = c(.2, .7),
    legend.justification = c("left", "bottom"),
    legend.box.just = "left",
    legend.margin = margin(6, 6, 6, 6)
    ) + theme(axis.text=element_text(size=12),
        axis.title=element_text(size=12,face="bold")) + theme(legend.text = element_text(size=12)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black")) +
  xlab("Self-Esteem") + ylab("Confidence")
SE.outdeg.Conf.Plot

Dialectical Self-Views

m<-lmer( confidence.Z ~ DS.Z*valence + ( valence | subID ) + ( DS.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
r2beta(m)

                Effect   Rsq upper.CL lower.CL
1                Model 0.014    0.017    0.011
3      valencepositive 0.005    0.007    0.003
2                 DS.Z 0.002    0.004    0.001
4 DS.Z:valencepositive 0.001    0.002    0.000

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.051 (-0.149 – 0.046)	0.049	-1.036	0.301	270.186
DS Z	-0.054 (-0.148 – 0.040)	0.048	-1.137	0.257	233.407
valence [positive]	0.111 (0.049 – 0.173)	0.032	3.511	<0.001	428.533
DS Z * valence [positive]	-0.044 (-0.094 – 0.006)	0.025	-1.749	0.082	239.744
Random Effects
σ2	0.54
τ00 traits	0.03
τ00 subID	0.52
τ11 traits.DS.Z	0.00
τ11 subID.valencepositive	0.13
ρ01 traits	0.33
ρ01 subID	-0.63
ICC	0.46
N subID	234
N traits	296
Observations	34215
Marginal R2 / Conditional R2	0.009 / 0.460

Plot

m<-lmer( confidence ~ DS*valence + ( valence | subID ) + ( DS | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

p <- ggpredict(m, c("DS","valence"))
DS.outdeg.Conf.Plot <-ggplot(p, aes(x, predicted)) +  geom_line(aes(linetype=group, color=group)) + geom_ribbon(aes(ymin=conf.low, ymax=conf.high, fill=group), alpha=0.15) + scale_linetype_discrete(labels = c("Negative", "Positive")) + scale_color_manual(labels = c("Negative", "Positive"), values = wes_palette("Darjeeling1")) + scale_fill_manual( 
                      labels=c("Negative", "Positive"), values = wes_palette("Darjeeling1")) + theme(
    legend.position = c(.2, .7),
    legend.justification = c("left", "bottom"),
    legend.box.just = "left",
    legend.margin = margin(6, 6, 6, 6)
    ) + theme(axis.text=element_text(size=12),
        axis.title=element_text(size=12,face="bold")) + theme(legend.text = element_text(size=12)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black")) +
  xlab("Dialectical Self-Views") + ylab("Confidence")
DS.outdeg.Conf.Plot

Interoceptive Awareness

m<-lmer( confidence.Z ~ MAIA.Z*valence + ( valence | subID ) + ( MAIA.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
r2beta(m)

                  Effect   Rsq upper.CL lower.CL
1                  Model 0.033    0.038    0.029
2                 MAIA.Z 0.010    0.013    0.008
3        valencepositive 0.005    0.006    0.003
4 MAIA.Z:valencepositive 0.001    0.001    0.000

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.054 (-0.149 – 0.042)	0.049	-1.099	0.273	273.623
MAIA Z	0.116 (0.024 – 0.208)	0.047	2.488	0.014	235.114
valence [positive]	0.109 (0.047 – 0.171)	0.031	3.475	0.001	431.604
MAIA Z * valence [positive]	0.041 (-0.008 – 0.090)	0.025	1.630	0.104	238.787
Random Effects
σ2	0.54
τ00 traits	0.03
τ00 subID	0.51
τ11 traits.MAIA.Z	0.00
τ11 subID.valencepositive	0.13
ρ01 traits	-0.47
ρ01 subID	-0.64
ICC	0.45
N subID	236
N traits	296
Observations	34512
Marginal R2 / Conditional R2	0.022 / 0.458

Plot

m<-lmer( confidence ~ MAIA*valence + ( valence | subID ) + ( MAIA | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

p <- ggpredict(m, c("MAIA","valence"))
MAIA.outdeg.Conf.Plot <-ggplot(p, aes(x, predicted)) +  geom_line(aes(linetype=group, color=group)) + geom_ribbon(aes(ymin=conf.low, ymax=conf.high, fill=group), alpha=0.15) + scale_linetype_discrete(labels = c("Negative", "Positive")) + scale_color_manual(labels = c("Negative", "Positive"), values = wes_palette("Darjeeling1")) + scale_fill_manual( 
                      labels=c("Negative", "Positive"), values = wes_palette("Darjeeling1")) + theme(
    legend.position = c(.2, .7),
    legend.justification = c("left", "bottom"),
    legend.box.just = "left",
    legend.margin = margin(6, 6, 6, 6)
    ) + theme(axis.text=element_text(size=12),
        axis.title=element_text(size=12,face="bold")) + theme(legend.text = element_text(size=12)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black")) +
  xlab("Interoceptive Awareness") + ylab("Confidence")
MAIA.outdeg.Conf.Plot

Depressive Symptoms

m<-lmer( confidence.Z ~ CESD.Z*valence + ( valence | subID ) + ( CESD.Z | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))
r2beta(m)

                  Effect   Rsq upper.CL lower.CL
1                  Model 0.008    0.010    0.006
3        valencepositive 0.005    0.006    0.003
4 CESD.Z:valencepositive 0.002    0.003    0.001
2                 CESD.Z 0.000    0.000    0.000

tab_model(m, collapse.ci = T, show.stat=T, show.r2 = T, show.se = T, string.pred = c("Fixed Effects"), string.est = "Coef.", string.se = "SE", string.stat = "t", digits = 3, emph.p = F, dv.labels = "Evaluation", df.method = "satterthwaite",show.df=T)

	Evaluation
Fixed Effects	Coef.	SE	t	p	df
(Intercept)	-0.060 (-0.157 – 0.038)	0.049	-1.208	0.228	270.233
CESD Z	-0.000 (-0.094 – 0.093)	0.048	-0.008	0.994	232.276
valence [positive]	0.110 (0.048 – 0.171)	0.031	3.492	0.001	429.051
CESD Z * valence [positive]	-0.063 (-0.112 – -0.015)	0.025	-2.561	0.011	231.331
Random Effects
σ2	0.55
τ00 traits	0.03
τ00 subID	0.52
τ11 traits.CESD.Z	0.00
τ11 subID.valencepositive	0.13
ρ01 traits	0.51
ρ01 subID	-0.62
ICC	0.45
N subID	234
N traits	296
Observations	34217
Marginal R2 / Conditional R2	0.005 / 0.456

Plot

m<-lmer( confidence ~ CESD*valence + ( valence | subID ) + ( CESD | traits), data=longDf, control=lmerControl(optimizer="bobyqa",
                                 optCtrl=list(maxfun=2e5)))

boundary (singular) fit: see help('isSingular')

Warning: Model failed to converge with 1 negative eigenvalue: -7.2e+03

p <- ggpredict(m, c("CESD","valence"))
CESD.outdeg.Conf.Plot <-ggplot(p, aes(x, predicted)) +  geom_line(aes(linetype=group, color=group)) + geom_ribbon(aes(ymin=conf.low, ymax=conf.high, fill=group), alpha=0.15) + scale_linetype_discrete(labels = c("Negative", "Positive")) + scale_color_manual(labels = c("Negative", "Positive"), values = wes_palette("Darjeeling1")) + scale_fill_manual( 
                      labels=c("Negative", "Positive"), values = wes_palette("Darjeeling1")) + theme(
    legend.position = c(.2, .7),
    legend.justification = c("left", "bottom"),
    legend.box.just = "left",
    legend.margin = margin(6, 6, 6, 6)
    ) + theme(axis.text=element_text(size=12),
        axis.title=element_text(size=12,face="bold")) + theme(legend.text = element_text(size=12)) + theme(panel.border = element_rect(colour = "black", fill = NA, size =1)) + theme(legend.title = element_blank()) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black")) +
  xlab("Depressive Symptoms") + ylab("Confidence")
CESD.outdeg.Conf.Plot