Group Cohesiveness in Robotic Swarms
Rebecca
#Session Paramters
options(scipen=999, digits = 2)Import Data
Descriptive Stats
dat_dvs <- dat %>%
select(synchro, group, react, figure, suivre)
dat_dvs <- as.data.frame(dat_dvs)
round(stat.desc(dat_dvs, norm = TRUE), digits = 2)## synchro group react figure suivre
## nbr.val 877.00 878.00 873.00 879.00 874.00
## nbr.null 0.00 0.00 0.00 0.00 0.00
## nbr.na 5.00 4.00 9.00 3.00 8.00
## min 1.00 1.00 1.00 1.00 1.00
## max 5.00 5.00 5.00 5.00 5.00
## range 4.00 4.00 4.00 4.00 4.00
## sum 3555.00 3254.00 3319.00 3265.00 2692.00
## median 5.00 4.00 4.00 4.00 3.00
## mean 4.05 3.71 3.80 3.71 3.08
## SE.mean 0.04 0.05 0.05 0.05 0.05
## CI.mean.0.95 0.08 0.09 0.09 0.09 0.09
## var 1.51 1.95 1.89 1.83 2.02
## std.dev 1.23 1.39 1.37 1.35 1.42
## coef.var 0.30 0.38 0.36 0.36 0.46
## skewness -1.23 -0.77 -0.99 -0.70 -0.01
## skew.2SE -7.43 -4.66 -5.96 -4.26 -0.06
## kurtosis 0.41 -0.74 -0.32 -0.77 -1.34
## kurt.2SE 1.23 -2.25 -0.97 -2.33 -4.05
## normtest.W 0.75 0.81 0.78 0.83 0.88
## normtest.p 0.00 0.00 0.00 0.00 0.00dat_animation <- dat %>%
select(animation, synchro, group, react, figure, suivre) %>%
group_by(animation) %>%
skim(animation, synchro, group, react, figure, suivre) %>%
select(skim_variable, animation, numeric.mean)
dat_animation## # A tibble: 45 x 3
## skim_variable animation numeric.mean
## <chr> <chr> <dbl>
## 1 synchro battery_2 4.20
## 2 synchro battery_3 4.38
## 3 synchro broken_comm 3.69
## 4 synchro close_comm 3.36
## 5 synchro init_comm_1 4.36
## 6 synchro init_comm_2 4.41
## 7 synchro intervention_1 3.73
## 8 synchro intervention_2 3.78
## 9 synchro no_problem 4.54
## 10 group battery_2 3.92
## # ... with 35 more rowsCorrelations
dat_cor <- dat %>%
select(init_com, fin_com, no_prob, intervention, battery, com_interrupted, synchro, group, react, figure, suivre)
dat_cor <- as.data.frame(dat_cor)
cor_matrix <- cor_mat(dat_cor, vars = NULL, method = "kendall", alternative = "two.sided", conf.level = 0.95)
cor_mark_significant(cor_matrix, cutpoints = c(0, 1e-04, 0.001, 0.01, 0.05, 1),
symbols = c("****", "***", "**", "*", ""))## rowname init_com fin_com no_prob intervention battery
## 1 init_com
## 2 fin_com 0.087**
## 3 no_prob 0.17**** 0.29****
## 4 intervention 0.075** 0.066* -0.061*
## 5 battery -0.027 0.17**** -0.011 0.31****
## 6 com_interrupted -0.014 0.21**** 0.15**** 0.15**** 0.31****
## 7 synchro 0.23**** 0.04 0.13**** -0.036 -0.1***
## 8 group 0.18**** -0.068* 0.056* 0.073** -0.022
## 9 react 0.2**** 0.023 0.045 0.011 -0.053
## 10 figure 0.12**** -0.036 0.095*** -0.008 -0.094***
## 11 suivre 0.11**** 0.046 0.092*** -0.001 0.0014
## com_interrupted synchro group react figure suivre
## 1
## 2
## 3
## 4
## 5
## 6
## 7 -0.12****
## 8 -0.11**** 0.46****
## 9 -0.063* 0.48**** 0.38****
## 10 -0.11**** 0.49**** 0.42**** 0.4****
## 11 -0.015 0.23**** 0.31**** 0.39**** 0.23****LMM
dat_melt <- melt(dat, id.vars = c("subject", "animation", "activite_corporelle", "jeux_videos", "animation_numerique"), measure.vars = c("synchro", "group", "react", "figure", "suivre"))
dat_melt <- dat_melt %>%
mutate(animation = fct_relevel(animation, c("init_comm_1", "intervention_1", "battery_2", "init_comm_2", "intervention_2", "battery_3", "no_problem", "broken_comm", "close_comm")))
model_tendance <- lmer(value ~ animation + variable + activite_corporelle + jeux_videos + animation_numerique + (1 | subject), data = dat_melt)
qqnorm(resid(model_tendance))
summary(model_tendance)## Linear mixed model fit by REML ['lmerMod']
## Formula: value ~ animation + variable + activite_corporelle + jeux_videos +
## animation_numerique + (1 | subject)
## Data: dat_melt
##
## REML criterion at convergence: 13995
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.135 -0.572 0.193 0.677 3.292
##
## Random effects:
## Groups Name Variance Std.Dev.
## subject (Intercept) 0.399 0.631
## Residual 1.331 1.154
## Number of obs: 4381, groups: subject, 98
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 4.0725 0.1814 22.45
## animationintervention_1 -0.1006 0.0741 -1.36
## animationbattery_2 0.2468 0.0739 3.34
## animationinit_comm_2 0.1614 0.0739 2.18
## animationintervention_2 -0.2257 0.0739 -3.05
## animationbattery_3 0.2533 0.0738 3.43
## animationno_problem 0.3708 0.0739 5.02
## animationbroken_comm -0.3509 0.0740 -4.74
## animationclose_comm -0.7418 0.0739 -10.03
## variablegroup -0.3451 0.0551 -6.27
## variablereact -0.2491 0.0552 -4.52
## variablefigure -0.3377 0.0551 -6.13
## variablesuivre -0.9720 0.0551 -17.63
## activite_corporelle 0.0495 0.0407 1.22
## jeux_videos -0.0450 0.0404 -1.11
## animation_numerique 0.0324 0.0437 0.74##
## Correlation matrix not shown by default, as p = 16 > 12.
## Use print(x, correlation=TRUE) or
## vcov(x) if you need itsumm(model_tendance, confint = TRUE)## MODEL INFO:
## Observations: 4381
## Dependent Variable: value
## Type: Mixed effects linear regression
##
## MODEL FIT:
## AIC = 14031.15, BIC = 14146.08
## Pseudo-R² (fixed effects) = 0.12
## Pseudo-R² (total) = 0.32
##
## FIXED EFFECTS:
## -------------------------------------------------------------------------------
## Est. 2.5% 97.5% t val. d.f. p
## ----------------------------- ------- ------- ------- -------- --------- ------
## (Intercept) 4.07 3.72 4.43 22.45 119.04 0.00
## animationintervention_1 -0.10 -0.25 0.04 -1.36 4271.29 0.17
## animationbattery_2 0.25 0.10 0.39 3.34 4271.12 0.00
## animationinit_comm_2 0.16 0.02 0.31 2.18 4271.12 0.03
## animationintervention_2 -0.23 -0.37 -0.08 -3.05 4271.14 0.00
## animationbattery_3 0.25 0.11 0.40 3.43 4271.09 0.00
## animationno_problem 0.37 0.23 0.52 5.02 4271.13 0.00
## animationbroken_comm -0.35 -0.50 -0.21 -4.74 4271.50 0.00
## animationclose_comm -0.74 -0.89 -0.60 -10.03 4271.13 0.00
## variablegroup -0.35 -0.45 -0.24 -6.27 4271.11 0.00
## variablereact -0.25 -0.36 -0.14 -4.52 4271.13 0.00
## variablefigure -0.34 -0.45 -0.23 -6.13 4271.10 0.00
## variablesuivre -0.97 -1.08 -0.86 -17.63 4271.12 0.00
## activite_corporelle 0.05 -0.03 0.13 1.22 94.07 0.23
## jeux_videos -0.05 -0.12 0.03 -1.11 94.03 0.27
## animation_numerique 0.03 -0.05 0.12 0.74 94.04 0.46
## -------------------------------------------------------------------------------
##
## p values calculated using Satterthwaite d.f.
##
## RANDOM EFFECTS:
## ------------------------------------
## Group Parameter Std. Dev.
## ---------- ------------- -----------
## subject (Intercept) 0.63
## Residual 1.15
## ------------------------------------
##
## Grouping variables:
## ---------------------------
## Group # groups ICC
## --------- ---------- ------
## subject 98 0.23
## ---------------------------tendance_lrt <- drop1(model_tendance, test = "Chisq")
tendance_lrt## Single term deletions
##
## Model:
## value ~ animation + variable + activite_corporelle + jeux_videos +
## animation_numerique + (1 | subject)
## npar AIC LRT Pr(Chi)
## <none> 13966
## animation 8 14305 354 <0.0000000000000002 ***
## variable 4 14285 327 <0.0000000000000002 ***
## activite_corporelle 1 13966 2 0.22
## jeux_videos 1 13966 1 0.26
## animation_numerique 1 13965 1 0.45
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1tendance_variable <- emmeans(model_tendance, "animation")## Note: D.f. calculations have been disabled because the number of observations exceeds 3000.
## To enable adjustments, add the argument 'pbkrtest.limit = 4381' (or larger)
## [or, globally, 'set emm_options(pbkrtest.limit = 4381)' or larger];
## but be warned that this may result in large computation time and memory use.## Note: D.f. calculations have been disabled because the number of observations exceeds 3000.
## To enable adjustments, add the argument 'lmerTest.limit = 4381' (or larger)
## [or, globally, 'set emm_options(lmerTest.limit = 4381)' or larger];
## but be warned that this may result in large computation time and memory use.tendance_variable## animation emmean SE df asymp.LCL asymp.UCL
## init_comm_1 3.7 0.082 Inf 3.6 3.9
## intervention_1 3.6 0.083 Inf 3.5 3.8
## battery_2 4.0 0.082 Inf 3.8 4.1
## init_comm_2 3.9 0.082 Inf 3.7 4.0
## intervention_2 3.5 0.082 Inf 3.3 3.7
## battery_3 4.0 0.082 Inf 3.8 4.1
## no_problem 4.1 0.082 Inf 3.9 4.2
## broken_comm 3.4 0.083 Inf 3.2 3.5
## close_comm 3.0 0.082 Inf 2.8 3.1
##
## Results are averaged over the levels of: variable
## Degrees-of-freedom method: asymptotic
## Confidence level used: 0.95variable_pairs <- pairs(tendance_variable)
print(summary(variable_pairs, adjust = "fdr", infer = c(TRUE, TRUE)), digits = 2)## contrast estimate SE df asymp.LCL asymp.UCL z.ratio
## init_comm_1 - intervention_1 0.10 0.074 Inf -0.14 0.34 1.400
## init_comm_1 - battery_2 -0.25 0.074 Inf -0.48 -0.01 -3.300
## init_comm_1 - init_comm_2 -0.16 0.074 Inf -0.40 0.07 -2.200
## init_comm_1 - intervention_2 0.23 0.074 Inf -0.01 0.46 3.100
## init_comm_1 - battery_3 -0.25 0.074 Inf -0.49 -0.02 -3.400
## init_comm_1 - no_problem -0.37 0.074 Inf -0.61 -0.13 -5.000
## init_comm_1 - broken_comm 0.35 0.074 Inf 0.11 0.59 4.700
## init_comm_1 - close_comm 0.74 0.074 Inf 0.51 0.98 10.000
## intervention_1 - battery_2 -0.35 0.074 Inf -0.58 -0.11 -4.700
## intervention_1 - init_comm_2 -0.26 0.074 Inf -0.50 -0.03 -3.500
## intervention_1 - intervention_2 0.13 0.074 Inf -0.11 0.36 1.700
## intervention_1 - battery_3 -0.35 0.074 Inf -0.59 -0.12 -4.800
## intervention_1 - no_problem -0.47 0.074 Inf -0.71 -0.23 -6.400
## intervention_1 - broken_comm 0.25 0.074 Inf 0.01 0.49 3.400
## intervention_1 - close_comm 0.64 0.074 Inf 0.40 0.88 8.600
## battery_2 - init_comm_2 0.09 0.074 Inf -0.15 0.32 1.200
## battery_2 - intervention_2 0.47 0.074 Inf 0.24 0.71 6.400
## battery_2 - battery_3 -0.01 0.074 Inf -0.24 0.23 -0.100
## battery_2 - no_problem -0.12 0.074 Inf -0.36 0.11 -1.700
## battery_2 - broken_comm 0.60 0.074 Inf 0.36 0.83 8.100
## battery_2 - close_comm 0.99 0.074 Inf 0.75 1.22 13.400
## init_comm_2 - intervention_2 0.39 0.074 Inf 0.15 0.62 5.200
## init_comm_2 - battery_3 -0.09 0.074 Inf -0.33 0.14 -1.200
## init_comm_2 - no_problem -0.21 0.074 Inf -0.45 0.03 -2.800
## init_comm_2 - broken_comm 0.51 0.074 Inf 0.28 0.75 6.900
## init_comm_2 - close_comm 0.90 0.074 Inf 0.67 1.14 12.200
## intervention_2 - battery_3 -0.48 0.074 Inf -0.72 -0.24 -6.500
## intervention_2 - no_problem -0.60 0.074 Inf -0.83 -0.36 -8.100
## intervention_2 - broken_comm 0.13 0.074 Inf -0.11 0.36 1.700
## intervention_2 - close_comm 0.52 0.074 Inf 0.28 0.75 7.000
## battery_3 - no_problem -0.12 0.074 Inf -0.35 0.12 -1.600
## battery_3 - broken_comm 0.60 0.074 Inf 0.37 0.84 8.200
## battery_3 - close_comm 1.00 0.074 Inf 0.76 1.23 13.500
## no_problem - broken_comm 0.72 0.074 Inf 0.49 0.96 9.700
## no_problem - close_comm 1.11 0.074 Inf 0.88 1.35 15.000
## broken_comm - close_comm 0.39 0.074 Inf 0.15 0.63 5.300
## p.value
## 0.1900
## <.0001
## 0.0400
## <.0001
## <.0001
## <.0001
## <.0001
## <.0001
## <.0001
## <.0001
## 0.1100
## <.0001
## <.0001
## <.0001
## <.0001
## 0.2500
## <.0001
## 0.9300
## 0.1100
## <.0001
## <.0001
## <.0001
## 0.2300
## 0.0100
## <.0001
## <.0001
## <.0001
## <.0001
## 0.1100
## <.0001
## 0.1300
## <.0001
## <.0001
## <.0001
## <.0001
## <.0001
##
## Results are averaged over the levels of: variable
## Degrees-of-freedom method: asymptotic
## Confidence level used: 0.95
## Conf-level adjustment: bonferroni method for 36 estimates
## P value adjustment: fdr method for 36 testsdat_gg <- dat_melt %>%
select(animation, value) %>%
mutate(animation = fct_relevel(animation, c("no_problem", "battery_2", "battery_3", "init_comm_2", "init_comm_1", "intervention_1", "intervention_2", "broken_comm", "close_comm")))
dat_gg %>%
dplyr::group_by(animation) %>%
skim(value)| Name | Piped data |
| Number of rows | 4410 |
| Number of columns | 2 |
| _______________________ | |
| Column type frequency: | |
| numeric | 1 |
| ________________________ | |
| Group variables | animation |
Variable type: numeric
| skim_variable | animation | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|
| value | no_problem | 3 | 0.99 | 4.1 | 1.4 | 1 | 4 | 5 | 5 | 5 | ▂▁▁▃▇ |
| value | battery_2 | 2 | 1.00 | 4.0 | 1.4 | 1 | 3 | 5 | 5 | 5 | ▂▁▂▃▇ |
| value | battery_3 | 0 | 1.00 | 4.0 | 1.3 | 1 | 3 | 5 | 5 | 5 | ▂▁▂▃▇ |
| value | init_comm_2 | 2 | 1.00 | 3.9 | 1.3 | 1 | 3 | 4 | 5 | 5 | ▂▁▂▅▇ |
| value | init_comm_1 | 3 | 0.99 | 3.7 | 1.4 | 1 | 3 | 4 | 5 | 5 | ▃▂▂▅▇ |
| value | intervention_1 | 8 | 0.98 | 3.6 | 1.4 | 1 | 3 | 4 | 5 | 5 | ▃▂▃▇▇ |
| value | intervention_2 | 3 | 0.99 | 3.5 | 1.4 | 1 | 2 | 4 | 5 | 5 | ▃▃▃▆▇ |
| value | broken_comm | 5 | 0.99 | 3.4 | 1.3 | 1 | 2 | 3 | 4 | 5 | ▃▅▇▇▇ |
| value | close_comm | 3 | 0.99 | 3.0 | 1.2 | 1 | 2 | 3 | 4 | 5 | ▂▇▆▅▃ |
pwc_animation <- dat_melt %>%
wilcox_test(value ~ animation, paired = TRUE, p.adjust.method = "fdr", detailed = TRUE) %>%
arrange(p.adj)
gg_animations <- ggplot(dat_gg, aes(x = animation, y = value)) +
stat_summary(fun = mean, geom = "bar", fill = "#A11A5BFF", alpha = 0.8, color = "#A11A5BFF", size = 1, width = 0.75, na.rm = TRUE) +
stat_summary(fun.data = mean_cl_boot, geom = "errorbar", na.rm = TRUE, position=position_dodge(1), color = "#03051AFF", width=.2, size=0.8) +
xlab("Animation") +
ylab("Mean Group Cohesiveness") +
scale_x_discrete(labels = c(init_comm_1 = "Seq. 1", intervention_1 = "Seq. 2", battery_2 = "Seq. 3", init_comm_2 = "Seq. 4", intervention_2 = "Seq. 5", battery_3 = "Seq. 6", no_problem = "Seq. 7", broken_comm = "Seq. 8", close_comm = "Seq. 9")) +
scale_y_continuous(breaks = seq(1,5,by = 1)) +
theme(axis.text = element_text(size=16)) +
theme(axis.title = element_text(size=16, face = "bold")) +
theme(axis.text.y = element_text(colour = "black")) +
theme(axis.text.x = element_text(colour = "black"))
gg_animations
Interaction
model_interact <- lmer(value ~ animation*variable + activite_corporelle + jeux_videos + animation_numerique + (1 | subject), data = dat_melt)
summ(model_interact)## MODEL INFO:
## Observations: 4381
## Dependent Variable: value
## Type: Mixed effects linear regression
##
## MODEL FIT:
## AIC = 13960.97, BIC = 14280.22
## Pseudo-R² (fixed effects) = 0.15
## Pseudo-R² (total) = 0.35
##
## FIXED EFFECTS:
## ------------------------------------------------------------------------------
## Est. S.E. t val. d.f.
## -------------------------------------------- ------- ------ -------- ---------
## (Intercept) 4.33 0.21 21.12 193.35
## animationintervention_1 -0.63 0.16 -3.89 4239.12
## animationbattery_2 -0.15 0.16 -0.95 4239.05
## animationinit_comm_2 0.05 0.16 0.32 4239.05
## animationintervention_2 -0.57 0.16 -3.50 4239.11
## animationbattery_3 0.02 0.16 0.13 4239.05
## animationno_problem 0.18 0.16 1.14 4239.05
## animationbroken_comm -0.66 0.16 -4.10 4239.13
## animationclose_comm -0.99 0.16 -6.10 4239.18
## variablegroup -0.57 0.16 -3.53 4239.05
## variablereact -0.57 0.16 -3.53 4239.05
## variablefigure -0.43 0.16 -2.65 4239.05
## variablesuivre -1.66 0.16 -10.16 4239.25
## activite_corporelle 0.05 0.04 1.22 94.06
## jeux_videos -0.04 0.04 -1.10 94.03
## animation_numerique 0.03 0.04 0.73 94.04
## animationintervention_1:variablegroup 0.87 0.23 3.78 4239.12
## animationbattery_2:variablegroup 0.29 0.23 1.25 4239.05
## animationinit_comm_2:variablegroup -0.05 0.23 -0.22 4239.05
## animationintervention_2:variablegroup 0.97 0.23 4.21 4239.15
## animationbattery_3:variablegroup 0.02 0.23 0.09 4239.05
## animationno_problem:variablegroup 0.29 0.23 1.25 4239.05
## animationbroken_comm:variablegroup -0.05 0.23 -0.21 4239.05
## animationclose_comm:variablegroup -0.27 0.23 -1.19 4239.11
## animationintervention_1:variablereact 0.58 0.23 2.50 4239.15
## animationbattery_2:variablereact 0.61 0.23 2.66 4239.08
## animationinit_comm_2:variablereact 0.20 0.23 0.87 4239.08
## animationintervention_2:variablereact 0.26 0.23 1.14 4239.08
## animationbattery_3:variablereact 0.55 0.23 2.41 4239.05
## animationno_problem:variablereact -0.11 0.23 -0.50 4239.12
## animationbroken_comm:variablereact 0.39 0.23 1.68 4239.05
## animationclose_comm:variablereact 0.43 0.23 1.88 4239.11
## animationintervention_1:variablefigure 0.53 0.23 2.31 4239.12
## animationbattery_2:variablefigure -0.02 0.23 -0.09 4239.08
## animationinit_comm_2:variablefigure 0.10 0.23 0.45 4239.05
## animationintervention_2:variablefigure -0.20 0.23 -0.86 4239.08
## animationbattery_3:variablefigure -0.19 0.23 -0.85 4239.05
## animationno_problem:variablefigure 0.32 0.23 1.38 4239.05
## animationbroken_comm:variablefigure 0.09 0.23 0.39 4239.05
## animationclose_comm:variablefigure 0.20 0.23 0.85 4239.11
## animationintervention_1:variablesuivre 0.69 0.23 2.99 4239.15
## animationbattery_2:variablesuivre 1.14 0.23 4.95 4239.15
## animationinit_comm_2:variablesuivre 0.31 0.23 1.36 4239.19
## animationintervention_2:variablesuivre 0.70 0.23 3.06 4239.17
## animationbattery_3:variablesuivre 0.80 0.23 3.48 4239.15
## animationno_problem:variablesuivre 0.45 0.23 1.96 4239.18
## animationbroken_comm:variablesuivre 1.15 0.23 5.00 4239.15
## animationclose_comm:variablesuivre 0.91 0.23 3.96 4239.24
## ------------------------------------------------------------------------------
##
## ---------------------------------------------------
## p
## -------------------------------------------- ------
## (Intercept) 0.00
## animationintervention_1 0.00
## animationbattery_2 0.34
## animationinit_comm_2 0.75
## animationintervention_2 0.00
## animationbattery_3 0.90
## animationno_problem 0.26
## animationbroken_comm 0.00
## animationclose_comm 0.00
## variablegroup 0.00
## variablereact 0.00
## variablefigure 0.01
## variablesuivre 0.00
## activite_corporelle 0.23
## jeux_videos 0.27
## animation_numerique 0.47
## animationintervention_1:variablegroup 0.00
## animationbattery_2:variablegroup 0.21
## animationinit_comm_2:variablegroup 0.82
## animationintervention_2:variablegroup 0.00
## animationbattery_3:variablegroup 0.93
## animationno_problem:variablegroup 0.21
## animationbroken_comm:variablegroup 0.84
## animationclose_comm:variablegroup 0.23
## animationintervention_1:variablereact 0.01
## animationbattery_2:variablereact 0.01
## animationinit_comm_2:variablereact 0.39
## animationintervention_2:variablereact 0.25
## animationbattery_3:variablereact 0.02
## animationno_problem:variablereact 0.62
## animationbroken_comm:variablereact 0.09
## animationclose_comm:variablereact 0.06
## animationintervention_1:variablefigure 0.02
## animationbattery_2:variablefigure 0.93
## animationinit_comm_2:variablefigure 0.66
## animationintervention_2:variablefigure 0.39
## animationbattery_3:variablefigure 0.40
## animationno_problem:variablefigure 0.17
## animationbroken_comm:variablefigure 0.70
## animationclose_comm:variablefigure 0.39
## animationintervention_1:variablesuivre 0.00
## animationbattery_2:variablesuivre 0.00
## animationinit_comm_2:variablesuivre 0.17
## animationintervention_2:variablesuivre 0.00
## animationbattery_3:variablesuivre 0.00
## animationno_problem:variablesuivre 0.05
## animationbroken_comm:variablesuivre 0.00
## animationclose_comm:variablesuivre 0.00
## ---------------------------------------------------
##
## p values calculated using Satterthwaite d.f.
##
## RANDOM EFFECTS:
## ------------------------------------
## Group Parameter Std. Dev.
## ---------- ------------- -----------
## subject (Intercept) 0.63
## Residual 1.13
## ------------------------------------
##
## Grouping variables:
## ---------------------------
## Group # groups ICC
## --------- ---------- ------
## subject 98 0.24
## ---------------------------Anova(model_interact, type = 3)## Analysis of Deviance Table (Type III Wald chisquare tests)
##
## Response: value
## Chisq Df Pr(>Chisq)
## (Intercept) 446.22 1 <0.0000000000000002 ***
## animation 103.17 8 <0.0000000000000002 ***
## variable 112.10 4 <0.0000000000000002 ***
## activite_corporelle 1.49 1 0.22
## jeux_videos 1.21 1 0.27
## animation_numerique 0.54 1 0.46
## animation:variable 195.31 32 <0.0000000000000002 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1drop1(model_interact, test = "Chisq")## Single term deletions
##
## Model:
## value ~ animation * variable + activite_corporelle + jeux_videos +
## animation_numerique + (1 | subject)
## npar AIC LRT Pr(Chi)
## <none> 13837
## activite_corporelle 1 13837 1.5 0.22
## jeux_videos 1 13837 1.3 0.26
## animation_numerique 1 13836 0.6 0.46
## animation:variable 32 13966 192.9 <0.0000000000000002 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1anova(model_tendance, model_interact)## refitting model(s) with ML (instead of REML)## Data: dat_melt
## Models:
## model_tendance: value ~ animation + variable + activite_corporelle + jeux_videos + animation_numerique + (1 | subject)
## model_interact: value ~ animation * variable + activite_corporelle + jeux_videos + animation_numerique + (1 | subject)
## npar AIC BIC logLik deviance Chisq Df Pr(>Chisq)
## model_tendance 18 13966 14081 -6965 13930
## model_interact 50 13837 14157 -6869 13737 193 32 <0.0000000000000002
##
## model_tendance
## model_interact ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1emm_posthoc <- emmeans(model_interact, pairwise ~ variable | animation, pbkrtest.limit = 4381)
emm_posthoc## $emmeans
## animation = init_comm_1:
## variable emmean SE df lower.CL upper.CL
## synchro 4.4 0.131 1214 4.1 4.6
## group 3.8 0.131 1214 3.5 4.0
## react 3.8 0.131 1214 3.5 4.0
## figure 3.9 0.131 1214 3.7 4.2
## suivre 2.7 0.133 1261 2.4 3.0
##
## animation = intervention_1:
## variable emmean SE df lower.CL upper.CL
## synchro 3.7 0.132 1229 3.5 4.0
## group 4.0 0.132 1229 3.8 4.3
## react 3.7 0.133 1277 3.5 4.0
## figure 3.8 0.132 1229 3.6 4.1
## suivre 2.8 0.132 1229 2.5 3.0
##
## animation = battery_2:
## variable emmean SE df lower.CL upper.CL
## synchro 4.2 0.131 1214 3.9 4.5
## group 3.9 0.131 1214 3.7 4.2
## react 4.2 0.132 1229 4.0 4.5
## figure 3.8 0.132 1229 3.5 4.0
## suivre 3.7 0.131 1214 3.4 3.9
##
## animation = init_comm_2:
## variable emmean SE df lower.CL upper.CL
## synchro 4.4 0.131 1214 4.2 4.7
## group 3.8 0.131 1214 3.5 4.0
## react 4.0 0.132 1229 3.8 4.3
## figure 4.1 0.131 1214 3.8 4.3
## suivre 3.1 0.132 1229 2.8 3.3
##
## animation = intervention_2:
## variable emmean SE df lower.CL upper.CL
## synchro 3.8 0.132 1229 3.5 4.0
## group 4.2 0.132 1245 3.9 4.4
## react 3.5 0.131 1214 3.2 3.7
## figure 3.2 0.131 1214 2.9 3.4
## suivre 2.8 0.131 1214 2.6 3.1
##
## animation = battery_3:
## variable emmean SE df lower.CL upper.CL
## synchro 4.4 0.131 1214 4.1 4.6
## group 3.8 0.131 1214 3.6 4.1
## react 4.4 0.131 1214 4.1 4.6
## figure 3.8 0.131 1214 3.5 4.0
## suivre 3.5 0.131 1214 3.3 3.8
##
## animation = no_problem:
## variable emmean SE df lower.CL upper.CL
## synchro 4.5 0.131 1214 4.3 4.8
## group 4.3 0.131 1214 4.0 4.5
## react 3.9 0.132 1245 3.6 4.1
## figure 4.4 0.131 1214 4.2 4.7
## suivre 3.3 0.132 1229 3.1 3.6
##
## animation = broken_comm:
## variable emmean SE df lower.CL upper.CL
## synchro 3.7 0.132 1229 3.4 4.0
## group 3.1 0.132 1229 2.8 3.3
## react 3.5 0.132 1229 3.2 3.8
## figure 3.4 0.132 1229 3.1 3.6
## suivre 3.2 0.132 1229 2.9 3.4
##
## animation = close_comm:
## variable emmean SE df lower.CL upper.CL
## synchro 3.4 0.132 1245 3.1 3.6
## group 2.5 0.131 1214 2.3 2.8
## react 3.2 0.131 1214 3.0 3.5
## figure 3.1 0.131 1214 2.9 3.4
## suivre 2.6 0.132 1229 2.4 2.9
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95
##
## $contrasts
## animation = init_comm_1:
## contrast estimate SE df t.ratio p.value
## synchro - group 0.57 0.162 4239 3.500 <.0001
## synchro - react 0.57 0.162 4239 3.500 <.0001
## synchro - figure 0.43 0.162 4239 2.600 0.0600
## synchro - suivre 1.66 0.163 4239 10.200 <.0001
## group - react 0.00 0.162 4239 0.000 1.0000
## group - figure -0.14 0.162 4239 -0.900 0.9000
## group - suivre 1.09 0.163 4239 6.700 <.0001
## react - figure -0.14 0.162 4239 -0.900 0.9000
## react - suivre 1.09 0.163 4239 6.700 <.0001
## figure - suivre 1.23 0.163 4239 7.500 <.0001
##
## animation = intervention_1:
## contrast estimate SE df t.ratio p.value
## synchro - group -0.30 0.163 4239 -1.800 0.3600
## synchro - react 0.00 0.164 4239 0.000 1.0000
## synchro - figure -0.10 0.163 4239 -0.600 0.9700
## synchro - suivre 0.97 0.163 4239 6.000 <.0001
## group - react 0.29 0.164 4239 1.800 0.3800
## group - figure 0.19 0.163 4239 1.200 0.7500
## group - suivre 1.27 0.163 4239 7.800 <.0001
## react - figure -0.10 0.164 4239 -0.600 0.9800
## react - suivre 0.97 0.164 4239 5.900 <.0001
## figure - suivre 1.07 0.163 4239 6.600 <.0001
##
## animation = battery_2:
## contrast estimate SE df t.ratio p.value
## synchro - group 0.29 0.162 4239 1.800 0.3900
## synchro - react -0.04 0.162 4239 -0.200 1.0000
## synchro - figure 0.45 0.162 4239 2.800 0.0400
## synchro - suivre 0.52 0.162 4239 3.200 0.0100
## group - react -0.32 0.162 4239 -2.000 0.2700
## group - figure 0.16 0.162 4239 1.000 0.8500
## group - suivre 0.23 0.162 4239 1.500 0.5900
## react - figure 0.49 0.163 4239 3.000 0.0200
## react - suivre 0.56 0.162 4239 3.400 0.0100
## figure - suivre 0.07 0.162 4239 0.400 0.9900
##
## animation = init_comm_2:
## contrast estimate SE df t.ratio p.value
## synchro - group 0.62 0.162 4239 3.800 <.0001
## synchro - react 0.37 0.162 4239 2.300 0.1500
## synchro - figure 0.33 0.162 4239 2.000 0.2600
## synchro - suivre 1.34 0.162 4239 8.300 <.0001
## group - react -0.25 0.162 4239 -1.500 0.5400
## group - figure -0.30 0.162 4239 -1.800 0.3600
## group - suivre 0.72 0.162 4239 4.400 <.0001
## react - figure -0.05 0.162 4239 -0.300 1.0000
## react - suivre 0.97 0.163 4239 6.000 <.0001
## figure - suivre 1.02 0.162 4239 6.300 <.0001
##
## animation = intervention_2:
## contrast estimate SE df t.ratio p.value
## synchro - group -0.40 0.163 4239 -2.400 0.1100
## synchro - react 0.31 0.162 4239 1.900 0.3100
## synchro - figure 0.63 0.162 4239 3.900 <.0001
## synchro - suivre 0.95 0.162 4239 5.900 <.0001
## group - react 0.71 0.163 4239 4.300 <.0001
## group - figure 1.02 0.163 4239 6.300 <.0001
## group - suivre 1.35 0.163 4239 8.300 <.0001
## react - figure 0.32 0.162 4239 2.000 0.2900
## react - suivre 0.64 0.162 4239 4.000 <.0001
## figure - suivre 0.33 0.162 4239 2.000 0.2600
##
## animation = battery_3:
## contrast estimate SE df t.ratio p.value
## synchro - group 0.55 0.162 4239 3.400 0.0100
## synchro - react 0.02 0.162 4239 0.100 1.0000
## synchro - figure 0.62 0.162 4239 3.800 <.0001
## synchro - suivre 0.86 0.162 4239 5.300 <.0001
## group - react -0.53 0.162 4239 -3.300 0.0100
## group - figure 0.07 0.162 4239 0.400 0.9900
## group - suivre 0.31 0.162 4239 1.900 0.3200
## react - figure 0.60 0.162 4239 3.700 <.0001
## react - suivre 0.84 0.162 4239 5.200 <.0001
## figure - suivre 0.23 0.162 4239 1.500 0.5900
##
## animation = no_problem:
## contrast estimate SE df t.ratio p.value
## synchro - group 0.29 0.162 4239 1.800 0.3900
## synchro - react 0.69 0.163 4239 4.200 <.0001
## synchro - figure 0.11 0.162 4239 0.700 0.9600
## synchro - suivre 1.21 0.162 4239 7.400 <.0001
## group - react 0.40 0.163 4239 2.500 0.1000
## group - figure -0.17 0.162 4239 -1.100 0.8200
## group - suivre 0.92 0.162 4239 5.700 <.0001
## react - figure -0.57 0.163 4239 -3.500 <.0001
## react - suivre 0.52 0.163 4239 3.200 0.0100
## figure - suivre 1.09 0.162 4239 6.700 <.0001
##
## animation = broken_comm:
## contrast estimate SE df t.ratio p.value
## synchro - group 0.62 0.163 4239 3.800 <.0001
## synchro - react 0.19 0.163 4239 1.100 0.7800
## synchro - figure 0.34 0.163 4239 2.100 0.2200
## synchro - suivre 0.51 0.163 4239 3.100 0.0200
## group - react -0.43 0.163 4239 -2.700 0.0600
## group - figure -0.28 0.163 4239 -1.700 0.4300
## group - suivre -0.11 0.163 4239 -0.700 0.9600
## react - figure 0.15 0.163 4239 1.000 0.8800
## react - suivre 0.32 0.163 4239 2.000 0.2800
## figure - suivre 0.16 0.163 4239 1.000 0.8500
##
## animation = close_comm:
## contrast estimate SE df t.ratio p.value
## synchro - group 0.85 0.163 4239 5.200 <.0001
## synchro - react 0.14 0.163 4239 0.900 0.9100
## synchro - figure 0.23 0.163 4239 1.400 0.6100
## synchro - suivre 0.75 0.163 4239 4.600 <.0001
## group - react -0.70 0.162 4239 -4.400 <.0001
## group - figure -0.61 0.162 4239 -3.800 <.0001
## group - suivre -0.10 0.162 4239 -0.600 0.9700
## react - figure 0.09 0.162 4239 0.600 0.9800
## react - suivre 0.60 0.162 4239 3.700 <.0001
## figure - suivre 0.51 0.162 4239 3.200 0.0100
##
## Degrees-of-freedom method: kenward-roger
## P value adjustment: tukey method for comparing a family of 5 estimatesemm_posthoc_corrected <- summary(emm_posthoc, adjust = "fdr", infer = c(TRUE, TRUE))
emm_posthoc_corrected## $emmeans
## animation = init_comm_1:
## variable emmean SE df lower.CL upper.CL t.ratio p.value
## synchro 4.4 0.131 1214 4.0 4.7 33.000 <.0001
## group 3.8 0.131 1214 3.4 4.1 29.000 <.0001
## react 3.8 0.131 1214 3.4 4.1 29.000 <.0001
## figure 3.9 0.131 1214 3.6 4.3 30.000 <.0001
## suivre 2.7 0.133 1261 2.4 3.0 20.000 <.0001
##
## animation = intervention_1:
## variable emmean SE df lower.CL upper.CL t.ratio p.value
## synchro 3.7 0.132 1229 3.4 4.1 28.000 <.0001
## group 4.0 0.132 1229 3.7 4.4 31.000 <.0001
## react 3.7 0.133 1277 3.4 4.1 28.000 <.0001
## figure 3.8 0.132 1229 3.5 4.2 29.000 <.0001
## suivre 2.8 0.132 1229 2.4 3.1 21.000 <.0001
##
## animation = battery_2:
## variable emmean SE df lower.CL upper.CL t.ratio p.value
## synchro 4.2 0.131 1214 3.9 4.5 32.000 <.0001
## group 3.9 0.131 1214 3.6 4.3 30.000 <.0001
## react 4.2 0.132 1229 3.9 4.6 32.000 <.0001
## figure 3.8 0.132 1229 3.4 4.1 29.000 <.0001
## suivre 3.7 0.131 1214 3.3 4.0 28.000 <.0001
##
## animation = init_comm_2:
## variable emmean SE df lower.CL upper.CL t.ratio p.value
## synchro 4.4 0.131 1214 4.1 4.7 34.000 <.0001
## group 3.8 0.131 1214 3.4 4.1 29.000 <.0001
## react 4.0 0.132 1229 3.7 4.4 31.000 <.0001
## figure 4.1 0.131 1214 3.7 4.4 31.000 <.0001
## suivre 3.1 0.132 1229 2.7 3.4 23.000 <.0001
##
## animation = intervention_2:
## variable emmean SE df lower.CL upper.CL t.ratio p.value
## synchro 3.8 0.132 1229 3.5 4.1 29.000 <.0001
## group 4.2 0.132 1245 3.8 4.5 32.000 <.0001
## react 3.5 0.131 1214 3.1 3.8 27.000 <.0001
## figure 3.2 0.131 1214 2.8 3.5 24.000 <.0001
## suivre 2.8 0.131 1214 2.5 3.2 22.000 <.0001
##
## animation = battery_3:
## variable emmean SE df lower.CL upper.CL t.ratio p.value
## synchro 4.4 0.131 1214 4.0 4.7 33.000 <.0001
## group 3.8 0.131 1214 3.5 4.2 29.000 <.0001
## react 4.4 0.131 1214 4.0 4.7 33.000 <.0001
## figure 3.8 0.131 1214 3.4 4.1 29.000 <.0001
## suivre 3.5 0.131 1214 3.2 3.9 27.000 <.0001
##
## animation = no_problem:
## variable emmean SE df lower.CL upper.CL t.ratio p.value
## synchro 4.5 0.131 1214 4.2 4.9 35.000 <.0001
## group 4.3 0.131 1214 3.9 4.6 32.000 <.0001
## react 3.9 0.132 1245 3.5 4.2 29.000 <.0001
## figure 4.4 0.131 1214 4.1 4.8 34.000 <.0001
## suivre 3.3 0.132 1229 3.0 3.7 25.000 <.0001
##
## animation = broken_comm:
## variable emmean SE df lower.CL upper.CL t.ratio p.value
## synchro 3.7 0.132 1229 3.4 4.0 28.000 <.0001
## group 3.1 0.132 1229 2.7 3.4 23.000 <.0001
## react 3.5 0.132 1229 3.2 3.8 27.000 <.0001
## figure 3.4 0.132 1229 3.0 3.7 25.000 <.0001
## suivre 3.2 0.132 1229 2.8 3.5 24.000 <.0001
##
## animation = close_comm:
## variable emmean SE df lower.CL upper.CL t.ratio p.value
## synchro 3.4 0.132 1245 3.0 3.7 25.000 <.0001
## group 2.5 0.131 1214 2.2 2.9 19.000 <.0001
## react 3.2 0.131 1214 2.9 3.6 25.000 <.0001
## figure 3.1 0.131 1214 2.8 3.5 24.000 <.0001
## suivre 2.6 0.132 1229 2.3 3.0 20.000 <.0001
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95
## Conf-level adjustment: bonferroni method for 5 estimates
## P value adjustment: fdr method for 5 tests
##
## $contrasts
## animation = init_comm_1:
## contrast estimate SE df lower.CL upper.CL t.ratio p.value
## synchro - group 0.57 0.162 4239 0.12 1.03 3.500 <.0001
## synchro - react 0.57 0.162 4239 0.12 1.03 3.500 <.0001
## synchro - figure 0.43 0.162 4239 -0.03 0.88 2.600 0.0100
## synchro - suivre 1.66 0.163 4239 1.20 2.12 10.200 <.0001
## group - react 0.00 0.162 4239 -0.45 0.45 0.000 1.0000
## group - figure -0.14 0.162 4239 -0.60 0.31 -0.900 0.4200
## group - suivre 1.09 0.163 4239 0.63 1.54 6.700 <.0001
## react - figure -0.14 0.162 4239 -0.60 0.31 -0.900 0.4200
## react - suivre 1.09 0.163 4239 0.63 1.54 6.700 <.0001
## figure - suivre 1.23 0.163 4239 0.77 1.69 7.500 <.0001
##
## animation = intervention_1:
## contrast estimate SE df lower.CL upper.CL t.ratio p.value
## synchro - group -0.30 0.163 4239 -0.75 0.16 -1.800 0.1200
## synchro - react 0.00 0.164 4239 -0.46 0.46 0.000 0.9800
## synchro - figure -0.10 0.163 4239 -0.56 0.35 -0.600 0.6100
## synchro - suivre 0.97 0.163 4239 0.51 1.43 6.000 <.0001
## group - react 0.29 0.164 4239 -0.17 0.75 1.800 0.1200
## group - figure 0.19 0.163 4239 -0.26 0.65 1.200 0.3300
## group - suivre 1.27 0.163 4239 0.81 1.72 7.800 <.0001
## react - figure -0.10 0.164 4239 -0.56 0.36 -0.600 0.6100
## react - suivre 0.97 0.164 4239 0.51 1.43 5.900 <.0001
## figure - suivre 1.07 0.163 4239 0.61 1.53 6.600 <.0001
##
## animation = battery_2:
## contrast estimate SE df lower.CL upper.CL t.ratio p.value
## synchro - group 0.29 0.162 4239 -0.17 0.74 1.800 0.1300
## synchro - react -0.04 0.162 4239 -0.49 0.42 -0.200 0.8100
## synchro - figure 0.45 0.162 4239 -0.01 0.91 2.800 0.0100
## synchro - suivre 0.52 0.162 4239 0.07 0.97 3.200 0.0100
## group - react -0.32 0.162 4239 -0.78 0.13 -2.000 0.0900
## group - figure 0.16 0.162 4239 -0.29 0.62 1.000 0.3900
## group - suivre 0.23 0.162 4239 -0.22 0.69 1.500 0.2100
## react - figure 0.49 0.163 4239 0.03 0.94 3.000 0.0100
## react - suivre 0.56 0.162 4239 0.10 1.01 3.400 0.0100
## figure - suivre 0.07 0.162 4239 -0.38 0.53 0.400 0.7400
##
## animation = init_comm_2:
## contrast estimate SE df lower.CL upper.CL t.ratio p.value
## synchro - group 0.62 0.162 4239 0.17 1.08 3.800 <.0001
## synchro - react 0.37 0.162 4239 -0.08 0.83 2.300 0.0400
## synchro - figure 0.33 0.162 4239 -0.13 0.78 2.000 0.0600
## synchro - suivre 1.34 0.162 4239 0.89 1.80 8.300 <.0001
## group - react -0.25 0.162 4239 -0.71 0.21 -1.500 0.1400
## group - figure -0.30 0.162 4239 -0.75 0.16 -1.800 0.0800
## group - suivre 0.72 0.162 4239 0.27 1.18 4.400 <.0001
## react - figure -0.05 0.162 4239 -0.50 0.41 -0.300 0.7800
## react - suivre 0.97 0.163 4239 0.51 1.43 6.000 <.0001
## figure - suivre 1.02 0.162 4239 0.56 1.47 6.300 <.0001
##
## animation = intervention_2:
## contrast estimate SE df lower.CL upper.CL t.ratio p.value
## synchro - group -0.40 0.163 4239 -0.85 0.06 -2.400 0.0200
## synchro - react 0.31 0.162 4239 -0.15 0.77 1.900 0.0600
## synchro - figure 0.63 0.162 4239 0.17 1.08 3.900 <.0001
## synchro - suivre 0.95 0.162 4239 0.50 1.41 5.900 <.0001
## group - react 0.71 0.163 4239 0.25 1.16 4.300 <.0001
## group - figure 1.02 0.163 4239 0.57 1.48 6.300 <.0001
## group - suivre 1.35 0.163 4239 0.89 1.81 8.300 <.0001
## react - figure 0.32 0.162 4239 -0.14 0.77 2.000 0.0600
## react - suivre 0.64 0.162 4239 0.19 1.10 4.000 <.0001
## figure - suivre 0.33 0.162 4239 -0.13 0.78 2.000 0.0500
##
## animation = battery_3:
## contrast estimate SE df lower.CL upper.CL t.ratio p.value
## synchro - group 0.55 0.162 4239 0.10 1.01 3.400 <.0001
## synchro - react 0.02 0.162 4239 -0.43 0.47 0.100 0.9000
## synchro - figure 0.62 0.162 4239 0.17 1.08 3.800 <.0001
## synchro - suivre 0.86 0.162 4239 0.40 1.31 5.300 <.0001
## group - react -0.53 0.162 4239 -0.98 -0.08 -3.300 <.0001
## group - figure 0.07 0.162 4239 -0.38 0.53 0.400 0.7300
## group - suivre 0.31 0.162 4239 -0.15 0.76 1.900 0.0800
## react - figure 0.60 0.162 4239 0.15 1.06 3.700 <.0001
## react - suivre 0.84 0.162 4239 0.38 1.29 5.200 <.0001
## figure - suivre 0.23 0.162 4239 -0.22 0.69 1.500 0.1800
##
## animation = no_problem:
## contrast estimate SE df lower.CL upper.CL t.ratio p.value
## synchro - group 0.29 0.162 4239 -0.17 0.74 1.800 0.1000
## synchro - react 0.69 0.163 4239 0.23 1.14 4.200 <.0001
## synchro - figure 0.11 0.162 4239 -0.34 0.57 0.700 0.4900
## synchro - suivre 1.21 0.162 4239 0.75 1.66 7.400 <.0001
## group - react 0.40 0.163 4239 -0.06 0.86 2.500 0.0200
## group - figure -0.17 0.162 4239 -0.63 0.28 -1.100 0.3200
## group - suivre 0.92 0.162 4239 0.46 1.38 5.700 <.0001
## react - figure -0.57 0.163 4239 -1.03 -0.12 -3.500 <.0001
## react - suivre 0.52 0.163 4239 0.06 0.98 3.200 <.0001
## figure - suivre 1.09 0.162 4239 0.64 1.55 6.700 <.0001
##
## animation = broken_comm:
## contrast estimate SE df lower.CL upper.CL t.ratio p.value
## synchro - group 0.62 0.163 4239 0.16 1.08 3.800 <.0001
## synchro - react 0.19 0.163 4239 -0.27 0.64 1.100 0.3600
## synchro - figure 0.34 0.163 4239 -0.12 0.80 2.100 0.0900
## synchro - suivre 0.51 0.163 4239 0.05 0.96 3.100 0.0100
## group - react -0.43 0.163 4239 -0.89 0.02 -2.700 0.0300
## group - figure -0.28 0.163 4239 -0.73 0.18 -1.700 0.1400
## group - suivre -0.11 0.163 4239 -0.57 0.34 -0.700 0.4900
## react - figure 0.15 0.163 4239 -0.30 0.61 1.000 0.3800
## react - suivre 0.32 0.163 4239 -0.14 0.78 2.000 0.1000
## figure - suivre 0.16 0.163 4239 -0.29 0.62 1.000 0.3800
##
## animation = close_comm:
## contrast estimate SE df lower.CL upper.CL t.ratio p.value
## synchro - group 0.85 0.163 4239 0.39 1.30 5.200 <.0001
## synchro - react 0.14 0.163 4239 -0.32 0.60 0.900 0.4800
## synchro - figure 0.23 0.163 4239 -0.22 0.69 1.400 0.2200
## synchro - suivre 0.75 0.163 4239 0.29 1.20 4.600 <.0001
## group - react -0.70 0.162 4239 -1.16 -0.25 -4.400 <.0001
## group - figure -0.61 0.162 4239 -1.07 -0.16 -3.800 <.0001
## group - suivre -0.10 0.162 4239 -0.56 0.36 -0.600 0.5700
## react - figure 0.09 0.162 4239 -0.36 0.55 0.600 0.5700
## react - suivre 0.60 0.162 4239 0.15 1.06 3.700 <.0001
## figure - suivre 0.51 0.162 4239 0.06 0.97 3.200 <.0001
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95
## Conf-level adjustment: bonferroni method for 10 estimates
## P value adjustment: fdr method for 10 testsGraph of Interaction
gg_interact <- cat_plot(model_interact, pred = animation, modx = variable, interval = TRUE, int.width = 0.95, outcome.scale = "response",
vary.lty = FALSE, geom = "bar",
x.label = "Animation Sequence",
y.label = "Average Group Tendency",
legend.main = "Group Characteristic",
pred.labels = c("Sequence 1", "Sequence 2", "Sequence 3", "Sequence 4", "Sequence 5", "Sequence 6", "Sequence 7", "Sequence 8", "Sequence 9"),
modx.labels = c("Synchronising", "Grouping", "Reacting", "Forming Figures", "Following"),
colors = c("#03051AFF", "#4C1D4BFF", "#A11A5BFF", "#E83F3FFF", "#F69C73FF"),
geom.alpha = 0.7) +
theme(axis.title.x = element_text(colour = "black"),
axis.title.y = element_text(colour = "black"),
axis.text.y = element_text(colour = "black"),
axis.text.x = element_text(colour = "black"),
legend.title = element_text(colour = "black"),
legend.text = element_text(colour = "black"),
axis.text = element_text(size = 12),
legend.position = "top")
gg_interact