Postural Stability and Emotions
Parkinson & Elder groups
Alvaro Rivera-Rei
13 septiembre, 2023
rm(list = ls()) # clean workspace
try(dev.off(), silent = TRUE) # close all plots
library(afex)
library(emmeans)
library(ggplot2)
library(ggridges)
library(ggdist)
library(dplyr)
library(reshape2)
library(GGally)
library(forcats)theme_set(
theme_minimal()
)
a_posteriori <- function(afex_aov, sig_level = .05) {
factors <- as.list(rownames(afex_aov$anova_table))
for (j in 1:length(factors)) {
if (grepl(":", factors[[j]])) {
factors[[j]] <- unlist(strsplit(factors[[j]], ":"))
}
}
p_values <- afex_aov$anova_table$`Pr(>F)`
for (i in 1:length(p_values)) {
if (p_values[i] <= sig_level) {
print(emmeans(afex_aov, factors[[i]], contr = "pairwise"))
cat(rep("_", 100), '\n', sep = "")
}
}
}master_dir <- '~/Insync/OneDrive_shared/Fondecyt_Emociones_Estabilometria'
data_dir <- paste(master_dir, 'data', sep = '/')
emo_data_name <- paste(data_dir, 'emo_data_clean.csv', sep='/')
emo_data_clean <- read.csv(emo_data_name, header = TRUE)
emo_data_clean <- emo_data_clean[(emo_data_clean$Group == 'Elder' | emo_data_clean$Group == 'Parkinson'), ]
emo_data_clean$Group <- factor(emo_data_clean$Group, levels = c("Parkinson", "Elder"))
emo_data_clean$Task <- factor(emo_data_clean$Task, levels = c("Unpleasant", "Neutral", "Pleasant"))
emo_data_clean$Emotion <- factor(emo_data_clean$Emotion)
emo_data_clean$ID <- factor(emo_data_clean$ID)
emo_data_clean$num_ID <- factor(emo_data_clean$num_ID)
emo_data_clean$log10_area <- log10(emo_data_clean$area)
emo_data_clean$log10_axis1 <- log10(emo_data_clean$axis1)
emo_data_clean$log10_axis2 <- log10(emo_data_clean$axis2)
emo_data_clean$log10_mdist <- log10(emo_data_clean$mdist)
emo_data_clean$log10_rmv <- log10(emo_data_clean$rmv)
emo_data_clean$log10_rmsx <- log10(emo_data_clean$rmsx)
emo_data_clean$log10_rmsy <- log10(emo_data_clean$rmsy)
emo_data_clean$log10_MPFx <- log10(emo_data_clean$MPFx)
emo_data_clean$log10_MPFy <- log10(emo_data_clean$MPFy)
emo_data_clean$log10_PEAKx <- log10(emo_data_clean$PEAKx)
emo_data_clean$log10_PEAKy <- log10(emo_data_clean$PEAKy)
emo_data_clean$log10_F50x <- log10(emo_data_clean$F50x)
emo_data_clean$log10_F50y <- log10(emo_data_clean$F50y)
emo_data_clean$log10_F95x <- log10(emo_data_clean$F95x)
emo_data_clean$log10_F95y <- log10(emo_data_clean$F95y)
emo_data_clean$log10_sampen_x <- log10(emo_data_clean$sampen_x)
emo_data_clean$log10_sampen_y <- log10(emo_data_clean$sampen_y)
emo_data_clean$log10_rMSSD <- log10(emo_data_clean$rMSSD)
emo_data_clean$log10_hrv_rmssd_nk2 <- log10(emo_data_clean$hrv_rmssd_nk2)
emo_data_clean$log10_ave_phasic_eda <- log10(emo_data_clean$ave_phasic_eda)Warning: NaNs producedemo_data_clean$rrv_rmssd[emo_data_clean$rrv_rmssd > 4500] <- NA
emo_data_clean$log10_scr_peaks_number <- log10(emo_data_clean$scr_peaks_number)
emo_data_clean$log10_scr_mean_amplitude <- log10(emo_data_clean$scr_mean_amplitude)
emo_data_clean[sapply(emo_data_clean, is.infinite)] <- NA1 General Description
filename Group Paradigm Task Emotion ID
Length:287 Parkinson:144 Length:287 Unpleasant:96 Yes:287 EP_201 : 3
Class :character Elder :143 Class :character Neutral :95 EP_202 : 3
Mode :character Mode :character Pleasant :96 EP_203 : 3
EP_204 : 3
EP_205 : 3
EP_206 : 3
(Other):269
area axis1 axis2 angle mdist
Min. : 35.77 Min. : 6.141 Min. : 1.799 Min. :-3.092 Min. : 2.224
1st Qu.: 145.26 1st Qu.:10.513 1st Qu.: 4.099 1st Qu.: 1.392 1st Qu.: 4.066
Median : 237.48 Median :13.133 Median : 5.727 Median : 1.561 Median : 5.057
Mean : 365.26 Mean :14.459 Mean : 6.757 Mean : 1.468 Mean : 5.615
3rd Qu.: 388.50 3rd Qu.:16.727 3rd Qu.: 7.912 3rd Qu.: 1.699 3rd Qu.: 6.480
Max. :4001.39 Max. :42.231 Max. :32.930 Max. : 3.102 Max. :17.666
rmv rmsx rmsy MPFx PEAKx
Min. : 5.410 Min. : 0.742 Min. : 2.500 Min. :0.0004269 Min. :0.0001221
1st Qu.: 8.682 1st Qu.: 1.865 1st Qu.: 4.065 1st Qu.:0.0012098 1st Qu.:0.0001221
Median :11.274 Median : 2.608 Median : 5.119 Median :0.0016730 Median :0.0001221
Mean :12.692 Mean : 3.155 Mean : 5.638 Mean :0.0019886 Mean :0.0003220
3rd Qu.:14.052 3rd Qu.: 3.664 3rd Qu.: 6.532 3rd Qu.:0.0025321 3rd Qu.:0.0002441
Max. :80.110 Max. :16.594 Max. :15.749 Max. :0.0110739 Max. :0.0065918
F50x F95x MPFy PEAKy F50y
Min. :0.0002441 Min. :0.001221 Min. :0.000437 Min. :0.0001221 Min. :0.0002441
1st Qu.:0.0002441 1st Qu.:0.004395 1st Qu.:0.001248 1st Qu.:0.0001221 1st Qu.:0.0006104
Median :0.0006104 Median :0.005737 Median :0.001738 Median :0.0002441 Median :0.0009766
Mean :0.0010497 Mean :0.006642 Mean :0.001851 Mean :0.0004721 Mean :0.0011088
3rd Qu.:0.0015869 3rd Qu.:0.007690 3rd Qu.:0.002238 3rd Qu.:0.0004883 3rd Qu.:0.0014648
Max. :0.0068359 Max. :0.042358 Max. :0.007089 Max. :0.0043945 Max. :0.0040283
F95y forward_mov sampen_x sampen_y sampen_resul_vect
Min. :0.001343 Min. :0.2373 Min. :0.00232 Min. :0.004815 Min. :0.01149
1st Qu.:0.003784 1st Qu.:0.4547 1st Qu.:0.10142 1st Qu.:0.052885 1st Qu.:1.64343
Median :0.005737 Median :0.5020 Median :0.22122 Median :0.097751 Median :1.98514
Mean :0.006240 Mean :0.4984 Mean :0.29223 Mean :0.120938 Mean :1.95572
3rd Qu.:0.008057 3rd Qu.:0.5444 3rd Qu.:0.37765 3rd Qu.:0.164868 3rd Qu.:2.27377
Max. :0.037598 Max. :0.8000 Max. :1.44107 Max. :0.490575 Max. :3.59382
NA's :14
sampen_phi_rad sampen_delta_phi heart_rate rMSSD ave_phasic_eda
Min. :0.4158 Min. :0.8149 Min. : 48.39 Min. : 2.789 Min. :-0.00002
1st Qu.:0.9228 1st Qu.:1.4124 1st Qu.: 67.08 1st Qu.: 7.814 1st Qu.: 0.04104
Median :1.0254 Median :1.5605 Median : 75.50 Median : 11.853 Median : 0.12315
Mean :1.0258 Mean :1.5459 Mean : 75.92 Mean : 26.921 Mean : 0.33144
3rd Qu.:1.1292 3rd Qu.:1.6750 3rd Qu.: 84.29 3rd Qu.: 24.402 3rd Qu.: 0.40055
Max. :1.5488 Max. :2.1407 Max. :111.18 Max. :834.339 Max. : 3.26276
NA's :25 NA's :25 NA's :23
ave_tonic_eda recurrence_rate_x determinism_x ave_diag_len_x longest_diag_x
Min. : 1.254 Min. :0.006863 Min. :0.9894 Min. : 6.371 Min. : 99.0
1st Qu.: 5.882 1st Qu.:0.062062 1st Qu.:0.9994 1st Qu.: 22.898 1st Qu.: 283.0
Median : 8.242 Median :0.084812 Median :0.9997 Median : 32.650 Median : 372.0
Mean :10.012 Mean :0.091064 Mean :0.9993 Mean : 38.817 Mean : 490.8
3rd Qu.:12.888 3rd Qu.:0.109634 3rd Qu.:0.9998 3rd Qu.: 46.795 3rd Qu.: 528.0
Max. :31.831 Max. :0.774053 Max. :1.0000 Max. :647.996 Max. :7464.0
NA's :23
diag_entropy_x laminarity_x trapping_time_x longest_vertical_x rec_time1_x
Min. :2.553 Min. :0.9743 Min. : 3.571 Min. : 27 Min. : 1.309
1st Qu.:3.976 1st Qu.:0.9996 1st Qu.: 28.059 1st Qu.: 291 1st Qu.: 9.249
Median :4.362 Median :0.9998 Median : 40.356 Median : 415 Median : 11.931
Mean :4.329 Mean :0.9995 Mean : 47.184 Mean : 492 Mean : 16.279
3rd Qu.:4.751 3rd Qu.:0.9999 3rd Qu.: 55.901 3rd Qu.: 594 3rd Qu.: 16.316
Max. :7.066 Max. :1.0000 Max. :824.210 Max. :3408 Max. :149.007
rec_time2_x rec_per_dens_entr_x clustering_x transitivity_x delay_x
Min. : 202.2 Min. :0.5353 Min. :0.2742 Min. :0.3536 Min. : 5.00
1st Qu.: 418.8 1st Qu.:0.6887 1st Qu.:0.5192 1st Qu.:0.5547 1st Qu.:22.00
Median : 499.4 Median :0.7169 Median :0.5551 Median :0.5962 Median :24.00
Mean : 510.2 Mean :0.7160 Mean :0.5534 Mean :0.5947 Mean :23.65
3rd Qu.: 565.2 3rd Qu.:0.7465 3rd Qu.:0.5879 3rd Qu.:0.6353 3rd Qu.:26.50
Max. :1391.6 Max. :0.8054 Max. :0.9388 Max. :0.9503 Max. :36.00
dim_x recurrence_rate_y determinism_y ave_diag_len_y longest_diag_y
Min. :2.000 Min. :0.01388 Min. :0.9924 Min. : 8.478 Min. : 88.0
1st Qu.:3.000 1st Qu.:0.06087 1st Qu.:0.9996 1st Qu.: 25.374 1st Qu.: 267.0
Median :3.000 Median :0.07875 Median :0.9998 Median : 33.149 Median : 342.0
Mean :3.098 Mean :0.07963 Mean :0.9996 Mean : 37.029 Mean : 394.9
3rd Qu.:3.000 3rd Qu.:0.09792 3rd Qu.:0.9999 3rd Qu.: 45.830 3rd Qu.: 453.5
Max. :4.000 Max. :0.21107 Max. :1.0000 Max. :107.322 Max. :2576.0
diag_entropy_y laminarity_y trapping_time_y longest_vertical_y rec_time1_y
Min. :2.764 Min. :0.9940 Min. : 7.05 Min. :114.0 Min. : 4.781
1st Qu.:4.118 1st Qu.:0.9997 1st Qu.: 29.67 1st Qu.:259.5 1st Qu.:10.346
Median :4.418 Median :0.9999 Median : 38.08 Median :340.0 Median :12.842
Mean :4.413 Mean :0.9997 Mean : 42.89 Mean :384.6 Mean :14.860
3rd Qu.:4.757 3rd Qu.:0.9999 3rd Qu.: 53.79 3rd Qu.:465.5 3rd Qu.:16.617
Max. :5.616 Max. :1.0000 Max. :135.14 Max. :906.0 Max. :73.026
rec_time2_y rec_per_dens_entr_y clustering_y transitivity_y delay_y
Min. : 238.9 Min. :0.6259 Min. :0.3494 Min. :0.3999 Min. : 7.00
1st Qu.: 461.2 1st Qu.:0.7363 1st Qu.:0.5225 1st Qu.:0.5576 1st Qu.:20.00
Median : 526.0 Median :0.7602 Median :0.5488 Median :0.5896 Median :22.00
Mean : 532.9 Mean :0.7549 Mean :0.5493 Mean :0.5878 Mean :21.68
3rd Qu.: 597.5 3rd Qu.:0.7789 3rd Qu.:0.5742 3rd Qu.:0.6197 3rd Qu.:24.00
Max. :1047.6 Max. :0.8367 Max. :0.7132 Max. :0.7432 Max. :34.00
dim_y delay_x2 dim_x2 tol_x2 delay_y2 dim_y2
Min. :2.000 Min. :15.00 Min. :6 Min. :1.422 Min. :15.00 Min. :5.00
1st Qu.:3.000 1st Qu.:15.25 1st Qu.:6 1st Qu.:1.496 1st Qu.:15.25 1st Qu.:5.25
Median :3.000 Median :15.50 Median :6 Median :1.571 Median :15.50 Median :5.50
Mean :3.059 Mean :15.50 Mean :6 Mean :1.571 Mean :15.50 Mean :5.50
3rd Qu.:3.000 3rd Qu.:15.75 3rd Qu.:6 3rd Qu.:1.645 3rd Qu.:15.75 3rd Qu.:5.75
Max. :4.000 Max. :16.00 Max. :6 Max. :1.720 Max. :16.00 Max. :6.00
NA's :285 NA's :285 NA's :285 NA's :285 NA's :285
tol_y2 rsp_rate rrv_rmssd rsa_porges scr_peaks_number
Min. :1.689 Min. : 4.309 Min. : 117.9 Min. :-11.321 Min. : 1.00
1st Qu.:1.782 1st Qu.:12.496 1st Qu.:1256.1 1st Qu.: -8.893 1st Qu.: 6.00
Median :1.874 Median :14.794 Median :1822.4 Median : -7.779 Median : 8.00
Mean :1.874 Mean :14.552 Mean :1877.1 Mean : -7.670 Mean : 12.62
3rd Qu.:1.967 3rd Qu.:16.467 3rd Qu.:2412.1 3rd Qu.: -6.622 3rd Qu.: 11.00
Max. :2.060 Max. :23.878 Max. :4469.5 Max. : -2.056 Max. :121.00
NA's :285 NA's :12
scr_mean_amplitude heart_rate_nk2 hrv_rmssd_nk2 num_ID log10_area
Min. :0.000e+00 Min. : 48.35 Min. : 2.742 201 : 6 Min. :1.554
1st Qu.:9.608e-06 1st Qu.: 67.36 1st Qu.: 7.364 202 : 6 1st Qu.:2.162
Median :3.305e-05 Median : 75.46 Median : 13.504 203 : 6 Median :2.376
Mean :1.571e-04 Mean : 76.05 Mean : 28.375 204 : 6 Mean :2.394
3rd Qu.:1.264e-04 3rd Qu.: 84.01 3rd Qu.: 27.840 205 : 6 3rd Qu.:2.589
Max. :1.051e-02 Max. :111.17 Max. :660.322 206 : 6 Max. :3.602
(Other):251
log10_axis1 log10_axis2 log10_mdist log10_rmv log10_rmsx
Min. :0.7882 Min. :0.2549 Min. :0.3471 Min. :0.7332 Min. :-0.1296
1st Qu.:1.0217 1st Qu.:0.6127 1st Qu.:0.6091 1st Qu.:0.9386 1st Qu.: 0.2706
Median :1.1184 Median :0.7579 Median :0.7039 Median :1.0521 Median : 0.4163
Mean :1.1288 Mean :0.7676 Mean :0.7180 Mean :1.0622 Mean : 0.4257
3rd Qu.:1.2234 3rd Qu.:0.8983 3rd Qu.:0.8115 3rd Qu.:1.1478 3rd Qu.: 0.5639
Max. :1.6256 Max. :1.5176 Max. :1.2471 Max. :1.9037 Max. : 1.2199
log10_rmsy log10_MPFx log10_MPFy log10_PEAKx log10_PEAKy
Min. :0.3979 Min. :-3.370 Min. :-3.360 Min. :-3.913 Min. :-3.913
1st Qu.:0.6090 1st Qu.:-2.917 1st Qu.:-2.904 1st Qu.:-3.913 1st Qu.:-3.913
Median :0.7092 Median :-2.777 Median :-2.760 Median :-3.913 Median :-3.612
Mean :0.7222 Mean :-2.765 Mean :-2.779 Mean :-3.728 Mean :-3.551
3rd Qu.:0.8150 3rd Qu.:-2.597 3rd Qu.:-2.650 3rd Qu.:-3.612 3rd Qu.:-3.311
Max. :1.1972 Max. :-1.956 Max. :-2.149 Max. :-2.181 Max. :-2.357
log10_F50x log10_F50y log10_F95x log10_F95y log10_sampen_x
Min. :-3.612 Min. :-3.612 Min. :-2.913 Min. :-2.872 Min. :-2.6345
1st Qu.:-3.612 1st Qu.:-3.214 1st Qu.:-2.357 1st Qu.:-2.422 1st Qu.:-0.9939
Median :-3.214 Median :-3.010 Median :-2.241 Median :-2.241 Median :-0.6552
Mean :-3.157 Mean :-3.033 Mean :-2.233 Mean :-2.260 Mean :-0.7296
3rd Qu.:-2.799 3rd Qu.:-2.834 3rd Qu.:-2.114 3rd Qu.:-2.094 3rd Qu.:-0.4229
Max. :-2.165 Max. :-2.395 Max. :-1.373 Max. :-1.425 Max. : 0.1587
log10_sampen_y log10_rMSSD log10_hrv_rmssd_nk2 log10_ave_phasic_eda log10_scr_peaks_number
Min. :-2.3174 Min. :0.4455 Min. :0.4381 Min. :-3.4462 Min. :0.0000
1st Qu.:-1.2767 1st Qu.:0.8929 1st Qu.:0.8671 1st Qu.:-1.3631 1st Qu.:0.7782
Median :-1.0099 Median :1.0738 Median :1.1305 Median :-0.8987 Median :0.9031
Mean :-1.0500 Mean :1.1636 Mean :1.1859 Mean :-0.9425 Mean :0.9500
3rd Qu.:-0.7829 3rd Qu.:1.3874 3rd Qu.:1.4447 3rd Qu.:-0.3960 3rd Qu.:1.0414
Max. :-0.3093 Max. :2.9213 Max. :2.8198 Max. : 0.5136 Max. :2.0828
NA's :25 NA's :25
log10_scr_mean_amplitude
Min. :-7.162
1st Qu.:-5.008
Median :-4.475
Mean :-4.496
3rd Qu.:-3.898
Max. :-1.978
NA's :1 1.1 Time-distance parameters
options(width = 100)
time_distance <- c('log10_area', 'log10_axis1', 'log10_axis2', 'log10_mdist', 'log10_rmv', 'log10_rmsx', 'log10_rmsy')
time_distance_pairs <- ggpairs(emo_data_clean,
columns = time_distance,
aes(colour = Group, alpha = .25),
progress = FALSE,
lower = list(continuous = wrap("points")))
suppressWarnings(print(time_distance_pairs))
log10_area log10_axis1 log10_axis2 log10_mdist log10_rmv
Min. :1.554 Min. :0.7882 Min. :0.2549 Min. :0.3471 Min. :0.7332
1st Qu.:2.162 1st Qu.:1.0217 1st Qu.:0.6127 1st Qu.:0.6091 1st Qu.:0.9386
Median :2.376 Median :1.1184 Median :0.7579 Median :0.7039 Median :1.0521
Mean :2.394 Mean :1.1288 Mean :0.7676 Mean :0.7180 Mean :1.0622
3rd Qu.:2.589 3rd Qu.:1.2234 3rd Qu.:0.8983 3rd Qu.:0.8115 3rd Qu.:1.1478
Max. :3.602 Max. :1.6256 Max. :1.5176 Max. :1.2471 Max. :1.9037
log10_rmsx log10_rmsy
Min. :-0.1296 Min. :0.3979
1st Qu.: 0.2706 1st Qu.:0.6090
Median : 0.4163 Median :0.7092
Mean : 0.4257 Mean :0.7222
3rd Qu.: 0.5639 3rd Qu.:0.8150
Max. : 1.2199 Max. :1.1972 1.2 Frequency parameters
options(width = 100)
frequency <- c('log10_MPFx', 'log10_MPFy', 'log10_PEAKx', 'log10_PEAKy', 'log10_F50x', 'log10_F50y', 'log10_F95x', 'log10_F95y')
frequency_pairs <- ggpairs(emo_data_clean,
columns = frequency,
aes(colour = Group, alpha = .25),
progress = FALSE,
lower = list(continuous = wrap("points")))
suppressWarnings(print(frequency_pairs))
log10_MPFx log10_MPFy log10_PEAKx log10_PEAKy log10_F50x
Min. :-3.370 Min. :-3.360 Min. :-3.913 Min. :-3.913 Min. :-3.612
1st Qu.:-2.917 1st Qu.:-2.904 1st Qu.:-3.913 1st Qu.:-3.913 1st Qu.:-3.612
Median :-2.777 Median :-2.760 Median :-3.913 Median :-3.612 Median :-3.214
Mean :-2.765 Mean :-2.779 Mean :-3.728 Mean :-3.551 Mean :-3.157
3rd Qu.:-2.597 3rd Qu.:-2.650 3rd Qu.:-3.612 3rd Qu.:-3.311 3rd Qu.:-2.799
Max. :-1.956 Max. :-2.149 Max. :-2.181 Max. :-2.357 Max. :-2.165
log10_F50y log10_F95x log10_F95y
Min. :-3.612 Min. :-2.913 Min. :-2.872
1st Qu.:-3.214 1st Qu.:-2.357 1st Qu.:-2.422
Median :-3.010 Median :-2.241 Median :-2.241
Mean :-3.033 Mean :-2.233 Mean :-2.260
3rd Qu.:-2.834 3rd Qu.:-2.114 3rd Qu.:-2.094
Max. :-2.395 Max. :-1.373 Max. :-1.425 1.3 Entropy
options(width = 100)
entropy <- c('forward_mov', 'log10_sampen_x', 'log10_sampen_y', 'sampen_resul_vect', 'sampen_phi_rad', 'sampen_delta_phi')
entropy_pairs <- ggpairs(emo_data_clean,
columns = entropy,
aes(colour = Group, alpha = .25),
progress = FALSE,
lower = list(continuous = wrap("points")))
suppressWarnings(print(entropy_pairs))
forward_mov log10_sampen_x log10_sampen_y sampen_resul_vect sampen_phi_rad
Min. :0.2373 Min. :-2.6345 Min. :-2.3174 Min. :0.01149 Min. :0.4158
1st Qu.:0.4547 1st Qu.:-0.9939 1st Qu.:-1.2767 1st Qu.:1.64343 1st Qu.:0.9228
Median :0.5020 Median :-0.6552 Median :-1.0099 Median :1.98514 Median :1.0254
Mean :0.4984 Mean :-0.7296 Mean :-1.0500 Mean :1.95572 Mean :1.0258
3rd Qu.:0.5444 3rd Qu.:-0.4229 3rd Qu.:-0.7829 3rd Qu.:2.27377 3rd Qu.:1.1292
Max. :0.8000 Max. : 0.1587 Max. :-0.3093 Max. :3.59382 Max. :1.5488
NA's :14
sampen_delta_phi
Min. :0.8149
1st Qu.:1.4124
Median :1.5605
Mean :1.5459
3rd Qu.:1.6750
Max. :2.1407
2 Classic Center of Pressure
60 seconds
2.1 Area (log10)
options(width = 100)
area_rep_anova <- aov_ez("ID", "log10_area", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47area_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_area, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(area_rain))
# area_group_rain <- ggplot(rep_anova_data, aes(y = fct_rev(Group), x = log10_area, color = Group, fill = Group)) +
# ggtitle("Area") +
# ylab("Group") +
# stat_halfeye(
# trim = FALSE,
# adjust = .75,
# .width = 0,
# justification = -.15,
# alpha = .4,
# point_colour = NA) +
# geom_boxplot(width = .15, alpha = .2, outlier.shape = NA) +
# geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05)) +
# theme(legend.position='none')
# suppressWarnings(print(area_group_rain))
# area_task_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_area, color = Task, fill = Task)) +
# ggtitle("Area") +
# ylab("Task") +
# stat_halfeye(
# trim = FALSE,
# adjust = .75,
# .width = 0,
# justification = -.15,
# alpha = .4,
# point_colour = NA) +
# geom_boxplot(width = .15, alpha = .2, outlier.shape = NA) +
# geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05)) +
# theme(legend.position='none')
# suppressWarnings(print(area_task_rain))
area_afex_plot <-
afex_plot(
area_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_area
Effect df MSE F ges p.value
1 Group 1, 93 0.23 23.38 *** .163 <.001
2 Task 1.98, 183.77 0.03 13.84 *** .033 <.001
3 Group:Task 1.98, 183.77 0.03 2.46 + .006 .089
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Group emmean SE df lower.CL upper.CL
Parkinson 2.53 0.0402 93 2.45 2.61
Elder 2.25 0.0407 93 2.17 2.34
Results are averaged over the levels of: Task
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson - Elder 0.277 0.0572 93 4.835 <.0001
Results are averaged over the levels of: Task
____________________________________________________________________________________________________
$emmeans
Task emmean SE df lower.CL upper.CL
Unpleasant 2.43 0.0336 93 2.37 2.50
Neutral 2.31 0.0295 93 2.25 2.37
Pleasant 2.43 0.0343 93 2.37 2.50
Results are averaged over the levels of: Group
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Unpleasant - Neutral 0.12294 0.0281 93 4.373 0.0001
Unpleasant - Pleasant 0.00125 0.0255 93 0.049 0.9987
Neutral - Pleasant -0.12169 0.0268 93 -4.539 <.0001
Results are averaged over the levels of: Group
P value adjustment: tukey method for comparing a family of 3 estimates
____________________________________________________________________________________________________2.2 Ellipse Major Axis (log10)
options(width = 100)
log10_axis1_rep_anova <- aov_ez("ID", "log10_axis1", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47log10_axis1_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_axis1, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(log10_axis1_rain))
log10_axis1_afex_plot <-
afex_plot(
log10_axis1_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_axis1
Effect df MSE F ges p.value
1 Group 1, 93 0.05 24.26 *** .168 <.001
2 Task 1.97, 183.51 0.01 22.44 *** .052 <.001
3 Group:Task 1.97, 183.51 0.01 0.32 <.001 .727
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Group emmean SE df lower.CL upper.CL
Parkinson 1.19 0.0183 93 1.16 1.23
Elder 1.06 0.0185 93 1.03 1.10
Results are averaged over the levels of: Task
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson - Elder 0.128 0.026 93 4.925 <.0001
Results are averaged over the levels of: Task
____________________________________________________________________________________________________
$emmeans
Task emmean SE df lower.CL upper.CL
Unpleasant 1.14 0.0144 93 1.11 1.17
Neutral 1.08 0.0144 93 1.05 1.11
Pleasant 1.16 0.0156 93 1.13 1.19
Results are averaged over the levels of: Group
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Unpleasant - Neutral 0.0592 0.0119 93 4.982 <.0001
Unpleasant - Pleasant -0.0197 0.0119 93 -1.654 0.2286
Neutral - Pleasant -0.0789 0.0130 93 -6.091 <.0001
Results are averaged over the levels of: Group
P value adjustment: tukey method for comparing a family of 3 estimates
____________________________________________________________________________________________________2.3 Ellipse Minor Axis (log10)
options(width = 100)
log10_axis2_rep_anova <- aov_ez("ID", "log10_axis2", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47log10_axis2_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_axis2, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(log10_axis2_rain))
log10_axis2_afex_plot <-
afex_plot(
log10_axis2_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_axis2
Effect df MSE F ges p.value
1 Group 1, 93 0.10 16.10 *** .112 <.001
2 Task 1.93, 179.72 0.02 5.54 ** .016 .005
3 Group:Task 1.93, 179.72 0.02 3.37 * .010 .038
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Group emmean SE df lower.CL upper.CL
Parkinson 0.842 0.0260 93 0.790 0.894
Elder 0.694 0.0263 93 0.641 0.746
Results are averaged over the levels of: Task
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson - Elder 0.148 0.037 93 4.012 0.0001
Results are averaged over the levels of: Task
____________________________________________________________________________________________________
$emmeans
Task emmean SE df lower.CL upper.CL
Unpleasant 0.796 0.0226 93 0.751 0.841
Neutral 0.732 0.0197 93 0.693 0.771
Pleasant 0.775 0.0225 93 0.730 0.820
Results are averaged over the levels of: Group
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Unpleasant - Neutral 0.0637 0.0212 93 3.000 0.0096
Unpleasant - Pleasant 0.0210 0.0188 93 1.113 0.5087
Neutral - Pleasant -0.0428 0.0184 93 -2.331 0.0565
Results are averaged over the levels of: Group
P value adjustment: tukey method for comparing a family of 3 estimates
____________________________________________________________________________________________________
$emmeans
Group Task emmean SE df lower.CL upper.CL
Parkinson Unpleasant 0.875 0.0319 93 0.812 0.939
Elder Unpleasant 0.716 0.0322 93 0.652 0.780
Parkinson Neutral 0.779 0.0277 93 0.724 0.834
Elder Neutral 0.686 0.0280 93 0.630 0.741
Parkinson Pleasant 0.871 0.0316 93 0.809 0.934
Elder Pleasant 0.679 0.0320 93 0.615 0.742
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson Unpleasant - Elder Unpleasant 0.15905 0.0453 93 3.511 0.0088
Parkinson Unpleasant - Parkinson Neutral 0.09667 0.0299 93 3.234 0.0203
Parkinson Unpleasant - Elder Neutral 0.18984 0.0424 93 4.476 0.0003
Parkinson Unpleasant - Parkinson Pleasant 0.00407 0.0265 93 0.154 1.0000
Parkinson Unpleasant - Elder Pleasant 0.19689 0.0451 93 4.362 0.0005
Elder Unpleasant - Parkinson Neutral -0.06238 0.0425 93 -1.469 0.6848
Elder Unpleasant - Elder Neutral 0.03079 0.0302 93 1.019 0.9104
Elder Unpleasant - Parkinson Pleasant -0.15499 0.0451 93 -3.433 0.0112
Elder Unpleasant - Elder Pleasant 0.03784 0.0268 93 1.414 0.7188
Parkinson Neutral - Elder Neutral 0.09317 0.0394 93 2.366 0.1792
Parkinson Neutral - Parkinson Pleasant -0.09260 0.0258 93 -3.587 0.0069
Parkinson Neutral - Elder Pleasant 0.10022 0.0423 93 2.369 0.1780
Elder Neutral - Parkinson Pleasant -0.18578 0.0422 93 -4.398 0.0004
Elder Neutral - Elder Pleasant 0.00705 0.0261 93 0.270 0.9998
Parkinson Pleasant - Elder Pleasant 0.19283 0.0450 93 4.287 0.0006
P value adjustment: tukey method for comparing a family of 6 estimates
____________________________________________________________________________________________________2.4 Mean Distance (log10)
options(width = 100)
mdist_rep_anova <- aov_ez("ID", "log10_mdist", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47mdist_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_mdist, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(mdist_rain))
mdist_afex_plot <-
afex_plot(
mdist_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_mdist
Effect df MSE F ges p.value
1 Group 1, 93 0.05 26.54 *** .183 <.001
2 Task 1.91, 177.51 0.01 17.33 *** .039 <.001
3 Group:Task 1.91, 177.51 0.01 0.92 .002 .396
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Group emmean SE df lower.CL upper.CL
Parkinson 0.785 0.0183 93 0.748 0.821
Elder 0.650 0.0185 93 0.614 0.687
Results are averaged over the levels of: Task
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson - Elder 0.134 0.0261 93 5.151 <.0001
Results are averaged over the levels of: Task
____________________________________________________________________________________________________
$emmeans
Task emmean SE df lower.CL upper.CL
Unpleasant 0.730 0.0142 93 0.702 0.758
Neutral 0.678 0.0144 93 0.649 0.706
Pleasant 0.744 0.0156 93 0.713 0.775
Results are averaged over the levels of: Group
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Unpleasant - Neutral 0.0521 0.0118 93 4.410 0.0001
Unpleasant - Pleasant -0.0143 0.0107 93 -1.334 0.3799
Neutral - Pleasant -0.0665 0.0130 93 -5.119 <.0001
Results are averaged over the levels of: Group
P value adjustment: tukey method for comparing a family of 3 estimates
____________________________________________________________________________________________________2.5 Root Mean Velocity (log10)
options(width = 100)
rmv_rep_anova <- aov_ez("ID", "log10_rmv", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47rmv_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_rmv, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(rmv_rain))
rmv_afex_plot <-
afex_plot(
rmv_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_rmv
Effect df MSE F ges p.value
1 Group 1, 93 0.07 18.40 *** .150 <.001
2 Task 2.00, 185.62 0.00 69.00 *** .074 <.001
3 Group:Task 2.00, 185.62 0.00 1.00 .001 .369
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Group emmean SE df lower.CL upper.CL
Parkinson 1.126 0.0213 93 1.084 1.17
Elder 0.996 0.0215 93 0.954 1.04
Results are averaged over the levels of: Task
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson - Elder 0.13 0.0302 93 4.290 <.0001
Results are averaged over the levels of: Task
____________________________________________________________________________________________________
$emmeans
Task emmean SE df lower.CL upper.CL
Unpleasant 1.08 0.0172 93 1.047 1.12
Neutral 1.00 0.0143 93 0.972 1.03
Pleasant 1.10 0.0164 93 1.069 1.13
Results are averaged over the levels of: Group
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Unpleasant - Neutral 0.0808 0.00920 93 8.787 <.0001
Unpleasant - Pleasant -0.0200 0.00918 93 -2.179 0.0802
Neutral - Pleasant -0.1008 0.00888 93 -11.353 <.0001
Results are averaged over the levels of: Group
P value adjustment: tukey method for comparing a family of 3 estimates
____________________________________________________________________________________________________2.6 Root Mean Square X (log10)
options(width = 100)
rmsx_rep_anova <- aov_ez("ID", "log10_rmsx", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47rmsx_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_rmsx, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(rmsx_rain))
rmsx_afex_plot <-
afex_plot(
rmsx_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_rmsx
Effect df MSE F ges p.value
1 Group 1, 93 0.11 14.75 *** .102 <.001
2 Task 1.94, 180.77 0.02 4.06 * .012 .020
3 Group:Task 1.94, 180.77 0.02 3.36 * .010 .038
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Group emmean SE df lower.CL upper.CL
Parkinson 0.502 0.0279 93 0.447 0.558
Elder 0.350 0.0282 93 0.294 0.406
Results are averaged over the levels of: Task
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson - Elder 0.152 0.0396 93 3.841 0.0002
Results are averaged over the levels of: Task
____________________________________________________________________________________________________
$emmeans
Task emmean SE df lower.CL upper.CL
Unpleasant 0.454 0.0245 93 0.405 0.502
Neutral 0.393 0.0208 93 0.352 0.435
Pleasant 0.431 0.0246 93 0.382 0.480
Results are averaged over the levels of: Group
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Unpleasant - Neutral 0.0605 0.0232 93 2.610 0.0282
Unpleasant - Pleasant 0.0228 0.0207 93 1.100 0.5167
Neutral - Pleasant -0.0377 0.0203 93 -1.858 0.1569
Results are averaged over the levels of: Group
P value adjustment: tukey method for comparing a family of 3 estimates
____________________________________________________________________________________________________
$emmeans
Group Task emmean SE df lower.CL upper.CL
Parkinson Unpleasant 0.532 0.0344 93 0.464 0.601
Elder Unpleasant 0.375 0.0348 93 0.306 0.445
Parkinson Neutral 0.441 0.0293 93 0.382 0.499
Elder Neutral 0.346 0.0296 93 0.287 0.405
Parkinson Pleasant 0.534 0.0346 93 0.465 0.602
Elder Pleasant 0.328 0.0350 93 0.259 0.398
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson Unpleasant - Elder Unpleasant 0.15687 0.0490 93 3.203 0.0222
Parkinson Unpleasant - Parkinson Neutral 0.09170 0.0326 93 2.811 0.0645
Parkinson Unpleasant - Elder Neutral 0.18623 0.0454 93 4.100 0.0012
Parkinson Unpleasant - Parkinson Pleasant -0.00145 0.0292 93 -0.050 1.0000
Parkinson Unpleasant - Elder Pleasant 0.20391 0.0491 93 4.154 0.0010
Elder Unpleasant - Parkinson Neutral -0.06517 0.0455 93 -1.432 0.7073
Elder Unpleasant - Elder Neutral 0.02936 0.0330 93 0.891 0.9479
Elder Unpleasant - Parkinson Pleasant -0.15832 0.0491 93 -3.225 0.0209
Elder Unpleasant - Elder Pleasant 0.04704 0.0295 93 1.596 0.6031
Parkinson Neutral - Elder Neutral 0.09453 0.0417 93 2.269 0.2172
Parkinson Neutral - Parkinson Pleasant -0.09314 0.0286 93 -3.260 0.0189
Parkinson Neutral - Elder Pleasant 0.11222 0.0456 93 2.459 0.1472
Elder Neutral - Parkinson Pleasant -0.18768 0.0455 93 -4.120 0.0011
Elder Neutral - Elder Pleasant 0.01769 0.0289 93 0.612 0.9899
Parkinson Pleasant - Elder Pleasant 0.20536 0.0492 93 4.173 0.0009
P value adjustment: tukey method for comparing a family of 6 estimates
____________________________________________________________________________________________________2.7 Root Mean Square Y (log10)
options(width = 100)
rmsy_rep_anova <- aov_ez("ID", "log10_rmsy", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47rmsy_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_rmsy, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(rmsy_rain))
rmsy_afex_plot <-
afex_plot(
rmsy_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_rmsy
Effect df MSE F ges p.value
1 Group 1, 93 0.04 25.56 *** .174 <.001
2 Task 1.93, 179.36 0.01 25.00 *** .059 <.001
3 Group:Task 1.93, 179.36 0.01 0.14 <.001 .860
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Group emmean SE df lower.CL upper.CL
Parkinson 0.785 0.0176 93 0.750 0.820
Elder 0.658 0.0178 93 0.623 0.693
Results are averaged over the levels of: Task
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson - Elder 0.127 0.025 93 5.056 <.0001
Results are averaged over the levels of: Task
____________________________________________________________________________________________________
$emmeans
Task emmean SE df lower.CL upper.CL
Unpleasant 0.734 0.0132 93 0.708 0.761
Neutral 0.674 0.0147 93 0.645 0.704
Pleasant 0.755 0.0149 93 0.726 0.785
Results are averaged over the levels of: Group
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Unpleasant - Neutral 0.0600 0.0116 93 5.169 <.0001
Unpleasant - Pleasant -0.0211 0.0111 93 -1.907 0.1425
Neutral - Pleasant -0.0811 0.0130 93 -6.259 <.0001
Results are averaged over the levels of: Group
P value adjustment: tukey method for comparing a family of 3 estimates
____________________________________________________________________________________________________2.8 Mean Power Frequency X (log10)
options(width = 100)
MPFx_rep_anova <- aov_ez("ID", "log10_MPFx", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47MPFx_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_MPFx, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(MPFx_rain))
MPFx_afex_plot <-
afex_plot(
MPFx_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_MPFx
Effect df MSE F ges p.value
1 Group 1, 93 0.10 0.14 <.001 .711
2 Task 1.98, 183.81 0.03 5.54 ** .020 .005
3 Group:Task 1.98, 183.81 0.03 2.61 + .010 .077
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Task emmean SE df lower.CL upper.CL
Unpleasant -2.75 0.0218 93 -2.80 -2.71
Neutral -2.81 0.0227 93 -2.85 -2.76
Pleasant -2.73 0.0262 93 -2.78 -2.68
Results are averaged over the levels of: Group
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Unpleasant - Neutral 0.0558 0.0232 93 2.403 0.0475
Unpleasant - Pleasant -0.0223 0.0238 93 -0.937 0.6182
Neutral - Pleasant -0.0781 0.0254 93 -3.075 0.0077
Results are averaged over the levels of: Group
P value adjustment: tukey method for comparing a family of 3 estimates
____________________________________________________________________________________________________2.9 Mean Power Frequency Y (log10)
options(width = 100)
MPFy_rep_anova <- aov_ez("ID", "log10_MPFy", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47MPFy_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_MPFy, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(MPFy_rain))
MPFy_afex_plot <-
afex_plot(
MPFy_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_MPFy
Effect df MSE F ges p.value
1 Group 1, 93 0.09 1.18 .009 .280
2 Task 1.97, 183.00 0.02 10.46 *** .027 <.001
3 Group:Task 1.97, 183.00 0.02 0.87 .002 .418
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Task emmean SE df lower.CL upper.CL
Unpleasant -2.77 0.0201 93 -2.81 -2.73
Neutral -2.83 0.0216 93 -2.87 -2.78
Pleasant -2.75 0.0210 93 -2.79 -2.71
Results are averaged over the levels of: Group
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Unpleasant - Neutral 0.0612 0.0186 93 3.284 0.0041
Unpleasant - Pleasant -0.0168 0.0168 93 -1.002 0.5775
Neutral - Pleasant -0.0779 0.0184 93 -4.242 0.0002
Results are averaged over the levels of: Group
P value adjustment: tukey method for comparing a family of 3 estimates
____________________________________________________________________________________________________2.10 Forward Movement
options(width = 100)
forward_mov_rep_anova <- aov_ez("ID", "forward_mov", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47forward_mov_rain <- ggplot(rep_anova_data, aes(y = Task, x = forward_mov, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(forward_mov_rain))
forward_mov_afex_plot <-
afex_plot(
forward_mov_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: forward_mov
Effect df MSE F ges p.value
1 Group 1, 93 0.01 0.01 <.001 .923
2 Task 1.96, 182.20 0.01 0.89 .006 .410
3 Group:Task 1.96, 182.20 0.01 2.60 + .016 .078
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG 3 Entropy and Center of Pressure
3.1 Sample Entropy X (log10)
options(width = 100)
log10_sampen_x_rep_anova <- aov_ez("ID", "log10_sampen_x", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47log10_sampen_x_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_sampen_x, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(log10_sampen_x_rain))
log10_sampen_x_afex_plot <-
afex_plot(
log10_sampen_x_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_sampen_x
Effect df MSE F ges p.value
1 Group 1, 93 0.40 7.04 ** .046 .009
2 Task 1.96, 182.73 0.11 0.63 .002 .531
3 Group:Task 1.96, 182.73 0.11 4.20 * .016 .017
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Group emmean SE df lower.CL upper.CL
Parkinson -0.829 0.0524 93 -0.933 -0.725
Elder -0.631 0.0529 93 -0.737 -0.526
Results are averaged over the levels of: Task
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson - Elder -0.198 0.0745 93 -2.653 0.0094
Results are averaged over the levels of: Task
____________________________________________________________________________________________________
$emmeans
Group Task emmean SE df lower.CL upper.CL
Parkinson Unpleasant -0.866 0.0651 93 -0.995 -0.736
Elder Unpleasant -0.657 0.0658 93 -0.788 -0.527
Parkinson Neutral -0.737 0.0603 93 -0.857 -0.617
Elder Neutral -0.686 0.0610 93 -0.807 -0.565
Parkinson Pleasant -0.884 0.0710 93 -1.025 -0.743
Elder Pleasant -0.551 0.0718 93 -0.694 -0.409
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson Unpleasant - Elder Unpleasant -0.2083 0.0926 93 -2.251 0.2252
Parkinson Unpleasant - Parkinson Neutral -0.1286 0.0729 93 -1.763 0.4943
Parkinson Unpleasant - Elder Neutral -0.1801 0.0892 93 -2.019 0.3395
Parkinson Unpleasant - Parkinson Pleasant 0.0185 0.0663 93 0.278 0.9998
Parkinson Unpleasant - Elder Pleasant -0.3145 0.0969 93 -3.246 0.0196
Elder Unpleasant - Parkinson Neutral 0.0797 0.0893 93 0.893 0.9472
Elder Unpleasant - Elder Neutral 0.0282 0.0737 93 0.383 0.9989
Elder Unpleasant - Parkinson Pleasant 0.2268 0.0968 93 2.343 0.1879
Elder Unpleasant - Elder Pleasant -0.1062 0.0670 93 -1.585 0.6104
Parkinson Neutral - Elder Neutral -0.0515 0.0858 93 -0.601 0.9907
Parkinson Neutral - Parkinson Pleasant 0.1470 0.0660 93 2.229 0.2347
Parkinson Neutral - Elder Pleasant -0.1860 0.0938 93 -1.984 0.3595
Elder Neutral - Parkinson Pleasant 0.1986 0.0936 93 2.121 0.2855
Elder Neutral - Elder Pleasant -0.1344 0.0667 93 -2.017 0.3409
Parkinson Pleasant - Elder Pleasant -0.3330 0.1010 93 -3.298 0.0168
P value adjustment: tukey method for comparing a family of 6 estimates
____________________________________________________________________________________________________3.2 Sample Entropy Y (log10)
options(width = 100)
log10_sampen_y_rep_anova <- aov_ez("ID", "log10_sampen_y", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47log10_sampen_y_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_sampen_y, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(log10_sampen_y_rain))
log10_sampen_y_afex_plot <-
afex_plot(
log10_sampen_y_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_sampen_y
Effect df MSE F ges p.value
1 Group 1, 93 0.28 16.67 *** .117 <.001
2 Task 1.96, 182.24 0.05 4.18 * .012 .017
3 Group:Task 1.96, 182.24 0.05 0.36 .001 .697
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Group emmean SE df lower.CL upper.CL
Parkinson -1.177 0.0438 93 -1.26 -1.090
Elder -0.922 0.0443 93 -1.01 -0.834
Results are averaged over the levels of: Task
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson - Elder -0.254 0.0623 93 -4.083 0.0001
Results are averaged over the levels of: Task
____________________________________________________________________________________________________
$emmeans
Task emmean SE df lower.CL upper.CL
Unpleasant -1.058 0.0322 93 -1.12 -0.994
Neutral -0.999 0.0376 93 -1.07 -0.924
Pleasant -1.091 0.0388 93 -1.17 -1.014
Results are averaged over the levels of: Group
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Unpleasant - Neutral -0.0595 0.0307 93 -1.940 0.1334
Unpleasant - Pleasant 0.0326 0.0316 93 1.030 0.5600
Neutral - Pleasant 0.0921 0.0345 93 2.669 0.0241
Results are averaged over the levels of: Group
P value adjustment: tukey method for comparing a family of 3 estimates
____________________________________________________________________________________________________3.3 Angle Sample Entropy
options(width = 100)
sampen_phi_rad_rep_anova <- aov_ez("ID", "sampen_phi_rad", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47sampen_phi_rad_rain <- ggplot(rep_anova_data, aes(y = Task, x = sampen_phi_rad, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(sampen_phi_rad_rain))
sampen_phi_rad_afex_plot <-
afex_plot(
sampen_phi_rad_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: sampen_phi_rad
Effect df MSE F ges p.value
1 Group 1, 93 0.08 0.03 <.001 .862
2 Task 2.00, 185.59 0.01 4.26 * .009 .016
3 Group:Task 2.00, 185.59 0.01 0.29 <.001 .747
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Task emmean SE df lower.CL upper.CL
Unpleasant 1.01 0.0178 93 0.972 1.04
Neutral 1.05 0.0190 93 1.012 1.09
Pleasant 1.02 0.0185 93 0.985 1.06
Results are averaged over the levels of: Group
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Unpleasant - Neutral -0.0416 0.0146 93 -2.848 0.0148
Unpleasant - Pleasant -0.0140 0.0147 93 -0.949 0.6108
Neutral - Pleasant 0.0276 0.0142 93 1.951 0.1304
Results are averaged over the levels of: Group
P value adjustment: tukey method for comparing a family of 3 estimates
____________________________________________________________________________________________________3.4 Resultant Vector Sample Entropy
options(width = 100)
sampen_resul_vect_rep_anova <- aov_ez("ID", "sampen_resul_vect", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 11 ID(s), which were removed before analysis:
EP_208, EP_229, EP_233, EP_234, FOSA_210, FOSA_225, FOSA_228, FOSA_232, FOSA_242, FOSA_243, ... [showing first 10 only]
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Grouprep_anova_data <- sampen_resul_vect_rep_anova$data$long
xtabs(~ Task + Group, data = rep_anova_data) Group
Task Parkinson Elder
Unpleasant 44 41
Neutral 44 41
Pleasant 44 41sampen_resul_vect_rain <- ggplot(rep_anova_data, aes(y = Task, x = sampen_resul_vect, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(sampen_resul_vect_rain))
sampen_resul_vect_afex_plot <-
afex_plot(
sampen_resul_vect_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: sampen_resul_vect
Effect df MSE F ges p.value
1 Group 1, 83 0.59 6.41 * .049 .013
2 Task 1.89, 156.89 0.15 17.23 *** .064 <.001
3 Group:Task 1.89, 156.89 0.15 0.17 <.001 .835
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Group emmean SE df lower.CL upper.CL
Parkinson 1.83 0.0671 83 1.70 1.96
Elder 2.07 0.0695 83 1.94 2.21
Results are averaged over the levels of: Task
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson - Elder -0.245 0.0966 83 -2.533 0.0132
Results are averaged over the levels of: Task
____________________________________________________________________________________________________
$emmeans
Task emmean SE df lower.CL upper.CL
Unpleasant 1.82 0.0658 83 1.69 1.95
Neutral 2.15 0.0547 83 2.04 2.26
Pleasant 1.89 0.0559 83 1.78 2.00
Results are averaged over the levels of: Group
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Unpleasant - Neutral -0.3253 0.0652 83 -4.989 <.0001
Unpleasant - Pleasant -0.0644 0.0567 83 -1.135 0.4952
Neutral - Pleasant 0.2610 0.0536 83 4.870 <.0001
Results are averaged over the levels of: Group
P value adjustment: tukey method for comparing a family of 3 estimates
____________________________________________________________________________________________________3.5 Angle Change Sample Entropy
options(width = 100)
sampen_delta_phi_rep_anova <- aov_ez("ID", "sampen_delta_phi", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47sampen_delta_phi_rain <- ggplot(rep_anova_data, aes(y = Task, x = sampen_delta_phi, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(sampen_delta_phi_rain))
sampen_delta_phi_afex_plot <-
afex_plot(
sampen_delta_phi_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: sampen_delta_phi
Effect df MSE F ges p.value
1 Group 1, 93 0.10 2.11 .016 .150
2 Task 2.00, 185.69 0.02 0.12 <.001 .890
3 Group:Task 2.00, 185.69 0.02 0.51 .001 .602
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG 4 Heart Activity
4.1 Heart Rate
options(width = 100)
heart_rate_rep_anova <- aov_ez("ID", "heart_rate", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 12 ID(s), which were removed before analysis:
EP_202, EP_204, EP_209, EP_222, EP_231, EP_235, EP_241, EP_245, FOSA_205, FOSA_210, ... [showing first 10 only]
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 40 44
Neutral 40 44
Pleasant 40 44heart_rate_rain <- ggplot(rep_anova_data, aes(y = Task, x = heart_rate, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(heart_rate_rain))
heart_rate_afex_plot <-
afex_plot(
heart_rate_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: heart_rate
Effect df MSE F ges p.value
1 Group 1, 82 422.26 0.75 .009 .390
2 Task 1.91, 156.97 7.71 5.50 ** .002 .006
3 Group:Task 1.91, 156.97 7.71 0.02 <.001 .976
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Task emmean SE df lower.CL upper.CL
Unpleasant 75.5 1.31 82 72.9 78.1
Neutral 76.0 1.31 82 73.4 78.6
Pleasant 76.9 1.34 82 74.2 79.5
Results are averaged over the levels of: Group
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Unpleasant - Neutral -0.467 0.383 82 -1.220 0.4451
Unpleasant - Pleasant -1.369 0.459 82 -2.983 0.0104
Neutral - Pleasant -0.902 0.413 82 -2.181 0.0805
Results are averaged over the levels of: Group
P value adjustment: tukey method for comparing a family of 3 estimates
____________________________________________________________________________________________________4.2 Heart Rate, NeuroKit2 method
options(width = 100)
heart_rate_nk2_rep_anova <- aov_ez("ID", "heart_rate_nk2", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47heart_rate_nk2_rain <- ggplot(rep_anova_data, aes(y = Task, x = heart_rate_nk2, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(heart_rate_nk2_rain))
heart_rate_nk2_afex_plot <-
afex_plot(
heart_rate_nk2_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: heart_rate_nk2
Effect df MSE F ges p.value
1 Group 1, 93 398.09 0.68 .007 .410
2 Task 1.68, 155.85 10.12 2.40 .001 .104
3 Group:Task 1.68, 155.85 10.12 0.73 <.001 .462
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG 4.3 Root Mean Square of the Successive Differences (log10)
options(width = 100)
rMSSD_rep_anova <- aov_ez("ID", "log10_rMSSD", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 12 ID(s), which were removed before analysis:
EP_202, EP_204, EP_209, EP_222, EP_231, EP_235, EP_241, EP_245, FOSA_205, FOSA_210, ... [showing first 10 only]
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 40 44
Neutral 40 44
Pleasant 40 44log10_rMSSD_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_rMSSD, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(log10_rMSSD_rain))
rMSSD_afex_plot <-
afex_plot(
rMSSD_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_rMSSD
Effect df MSE F ges p.value
1 Group 1, 82 0.44 0.02 <.001 .879
2 Task 1.94, 158.97 0.05 0.32 <.001 .721
3 Group:Task 1.94, 158.97 0.05 1.76 .004 .177
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG 4.4 Root Mean Square of the Successive Differences (log10), NeuroKit2 method
options(width = 100)
log10_hrv_rmssd_nk2_rep_anova <- aov_ez("ID", "log10_hrv_rmssd_nk2", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Grouprep_anova_data <- log10_hrv_rmssd_nk2_rep_anova$data$long
xtabs(~ Task + Group, data = rep_anova_data) Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47log10_hrv_rmssd_nk2_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_hrv_rmssd_nk2, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(log10_hrv_rmssd_nk2_rain))
log10_hrv_rmssd_nk2_afex_plot <-
afex_plot(
log10_hrv_rmssd_nk2_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_hrv_rmssd_nk2
Effect df MSE F ges p.value
1 Group 1, 93 0.43 0.00 <.001 .963
2 Task 1.79, 166.13 0.07 1.23 .003 .291
3 Group:Task 1.79, 166.13 0.07 1.67 .004 .194
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG 4.5 ECG-Derived Respiration
options(width = 100)
rsp_rate_rep_anova <- aov_ez("ID", "rsp_rate", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47rsp_rate_rain <- ggplot(rep_anova_data, aes(y = Task, x = rsp_rate, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(rsp_rate_rain))
rsp_rate_afex_plot <-
afex_plot(
rsp_rate_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: rsp_rate
Effect df MSE F ges p.value
1 Group 1, 93 19.66 1.52 .011 .220
2 Task 1.99, 185.19 4.08 1.59 .005 .207
3 Group:Task 1.99, 185.19 4.08 2.55 + .008 .081
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG 4.6 Root mean square of successive differences of the breath-to-breath intervals
options(width = 100)
rrv_rmssd_rep_anova <- aov_ez("ID", "rrv_rmssd", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 10 ID(s), which were removed before analysis:
EP_202, EP_209, EP_224, EP_231, EP_240, EP_247, FOSA_205, FOSA_210, FOSA_213, FOSA_229, ... [showing first 10 only]
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 42 44
Neutral 42 44
Pleasant 42 44rrv_rmssd_rain <- ggplot(rep_anova_data, aes(y = Task, x = rrv_rmssd, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(rrv_rmssd_rain))
rrv_rmssd_afex_plot <-
afex_plot(
rrv_rmssd_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: rrv_rmssd
Effect df MSE F ges p.value
1 Group 1, 84 1272648.32 1.21 .008 .275
2 Task 1.89, 158.93 530488.98 1.23 .006 .294
3 Group:Task 1.89, 158.93 530488.98 4.15 * .021 .019
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Group Task emmean SE df lower.CL upper.CL
Parkinson Unpleasant 1668 136 84 1398 1938
Elder Unpleasant 2175 133 84 1911 2439
Parkinson Neutral 1895 147 84 1602 2188
Elder Neutral 1810 144 84 1524 2096
Parkinson Pleasant 1732 119 84 1496 1968
Elder Pleasant 1774 116 84 1544 2005
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson Unpleasant - Elder Unpleasant -506.6 190 84 -2.671 0.0921
Parkinson Unpleasant - Parkinson Neutral -226.6 172 84 -1.319 0.7736
Parkinson Unpleasant - Elder Neutral -141.5 198 84 -0.715 0.9796
Parkinson Unpleasant - Parkinson Pleasant -63.9 142 84 -0.450 0.9976
Parkinson Unpleasant - Elder Pleasant -105.9 178 84 -0.593 0.9912
Elder Unpleasant - Parkinson Neutral 280.1 198 84 1.413 0.7191
Elder Unpleasant - Elder Neutral 365.1 168 84 2.176 0.2599
Elder Unpleasant - Parkinson Pleasant 442.8 178 84 2.489 0.1393
Elder Unpleasant - Elder Pleasant 400.7 139 84 2.892 0.0533
Parkinson Neutral - Elder Neutral 85.0 206 84 0.413 0.9984
Parkinson Neutral - Parkinson Pleasant 162.7 149 84 1.095 0.8822
Parkinson Neutral - Elder Pleasant 120.7 187 84 0.644 0.9873
Elder Neutral - Parkinson Pleasant 77.7 187 84 0.416 0.9983
Elder Neutral - Elder Pleasant 35.6 145 84 0.245 0.9999
Parkinson Pleasant - Elder Pleasant -42.0 166 84 -0.253 0.9999
P value adjustment: tukey method for comparing a family of 6 estimates
____________________________________________________________________________________________________4.7 Respiratory Sinus Arrhythmia, RSA (Porges-Bohrer algorithm)
options(width = 100)
rsa_porges_rep_anova <- aov_ez("ID", "rsa_porges", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Group Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47rsa_porges_rain <- ggplot(rep_anova_data, aes(y = Task, x = rsa_porges, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(rsa_porges_rain))
rsa_porges_afex_plot <-
afex_plot(
rsa_porges_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: rsa_porges
Effect df MSE F ges p.value
1 Group 1, 93 6.88 0.39 .003 .533
2 Task 1.95, 181.70 0.97 1.78 .004 .172
3 Group:Task 1.95, 181.70 0.97 3.66 * .008 .029
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Group Task emmean SE df lower.CL upper.CL
Parkinson Unpleasant -7.50 0.246 93 -7.99 -7.01
Elder Unpleasant -7.57 0.249 93 -8.06 -7.07
Parkinson Neutral -8.12 0.229 93 -8.57 -7.66
Elder Neutral -7.48 0.231 93 -7.94 -7.03
Parkinson Pleasant -7.67 0.264 93 -8.19 -7.14
Elder Pleasant -7.65 0.267 93 -8.18 -7.12
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson Unpleasant - Elder Unpleasant 0.0627 0.350 93 0.179 1.0000
Parkinson Unpleasant - Parkinson Neutral 0.6135 0.183 93 3.349 0.0145
Parkinson Unpleasant - Elder Neutral -0.0190 0.338 93 -0.056 1.0000
Parkinson Unpleasant - Parkinson Pleasant 0.1638 0.209 93 0.783 0.9698
Parkinson Unpleasant - Elder Pleasant 0.1505 0.363 93 0.415 0.9984
Elder Unpleasant - Parkinson Neutral 0.5508 0.338 93 1.630 0.5813
Elder Unpleasant - Elder Neutral -0.0817 0.185 93 -0.441 0.9978
Elder Unpleasant - Parkinson Pleasant 0.1011 0.363 93 0.279 0.9998
Elder Unpleasant - Elder Pleasant 0.0878 0.212 93 0.415 0.9984
Parkinson Neutral - Elder Neutral -0.6325 0.325 93 -1.945 0.3818
Parkinson Neutral - Parkinson Pleasant -0.4497 0.201 93 -2.236 0.2317
Parkinson Neutral - Elder Pleasant -0.4630 0.351 93 -1.317 0.7747
Elder Neutral - Parkinson Pleasant 0.1828 0.351 93 0.521 0.9952
Elder Neutral - Elder Pleasant 0.1695 0.203 93 0.834 0.9605
Parkinson Pleasant - Elder Pleasant -0.0133 0.375 93 -0.035 1.0000
P value adjustment: tukey method for comparing a family of 6 estimates
____________________________________________________________________________________________________5 Electrodermal Activity
Resultados muuuuuy tentativos por la calidad errática de los registros
5.1 Mean Phasic Component (log10)
options(width = 100)
log10_ave_phasic_eda_rep_anova = aov_ez("ID", "log10_ave_phasic_eda", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 17 ID(s), which were removed before analysis:
EP_202, EP_204, EP_205, EP_207, EP_208, EP_209, EP_217, EP_219, EP_221, EP_223, ... [showing first 10 only]
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Grouprep_anova_data <- log10_ave_phasic_eda_rep_anova$data$long
xtabs(~ Task + Group, data = rep_anova_data) Group
Task Parkinson Elder
Unpleasant 32 47
Neutral 32 47
Pleasant 32 47log10_ave_phasic_eda_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_ave_phasic_eda, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(log10_ave_phasic_eda_rain))
log10_ave_phasic_eda_afex_plot <-
afex_plot(
log10_ave_phasic_eda_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_ave_phasic_eda
Effect df MSE F ges p.value
1 Group 1, 77 1.21 0.00 <.001 .959
2 Task 1.97, 151.88 0.12 47.26 *** .089 <.001
3 Group:Task 1.97, 151.88 0.12 1.46 .003 .235
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Task emmean SE df lower.CL upper.CL
Unpleasant -0.662 0.0662 77 -0.794 -0.531
Neutral -1.196 0.0835 77 -1.363 -1.030
Pleasant -0.921 0.0867 77 -1.094 -0.749
Results are averaged over the levels of: Group
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Unpleasant - Neutral 0.534 0.0543 77 9.837 <.0001
Unpleasant - Pleasant 0.259 0.0579 77 4.466 0.0001
Neutral - Pleasant -0.275 0.0524 77 -5.248 <.0001
Results are averaged over the levels of: Group
P value adjustment: tukey method for comparing a family of 3 estimates
____________________________________________________________________________________________________5.2 Number of SCR Peaks (log10)
options(width = 100)
log10_scr_peaks_number_rep_anova <- aov_ez("ID", "log10_scr_peaks_number", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 1 ID(s), which were removed before analysis:
FOSA_210
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Grouprep_anova_data <- log10_scr_peaks_number_rep_anova$data$long
xtabs(~ Task + Group, data = rep_anova_data) Group
Task Parkinson Elder
Unpleasant 48 47
Neutral 48 47
Pleasant 48 47log10_scr_peaks_number_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_scr_peaks_number, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(log10_scr_peaks_number_rain))
log10_scr_peaks_number_afex_plot <-
afex_plot(
log10_scr_peaks_number_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_scr_peaks_number
Effect df MSE F ges p.value
1 Group 1, 93 0.19 9.89 ** .068 .002
2 Task 1.88, 174.62 0.04 2.94 + .010 .059
3 Group:Task 1.88, 174.62 0.04 1.08 .004 .337
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Group emmean SE df lower.CL upper.CL
Parkinson 1.029 0.0361 93 0.957 1.10
Elder 0.868 0.0364 93 0.795 0.94
Results are averaged over the levels of: Task
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Parkinson - Elder 0.161 0.0513 93 3.144 0.0022
Results are averaged over the levels of: Task
____________________________________________________________________________________________________5.3 Mean SCR Amplitude (log10)
options(width = 100)
log10_scr_mean_amplitude_rep_anova <- aov_ez("ID", "log10_scr_mean_amplitude", emo_data_clean, within = c("Task"), between = c("Group"))Warning: Missing values for 2 ID(s), which were removed before analysis:
FOSA_210, FOSA_213
Below the first few rows (in wide format) of the removed cases with missing data.
Contrasts set to contr.sum for the following variables: Grouprep_anova_data <- log10_scr_mean_amplitude_rep_anova$data$long
xtabs(~ Task + Group, data = rep_anova_data) Group
Task Parkinson Elder
Unpleasant 48 46
Neutral 48 46
Pleasant 48 46log10_scr_mean_amplitude_rain <- ggplot(rep_anova_data, aes(y = Task, x = log10_scr_mean_amplitude, color = Group, fill = Group)) +
stat_halfeye(
trim = FALSE,
.width = 0,
justification = -.15,
alpha = .4,
point_colour = NA) +
geom_point(size = 2, alpha = .4, position = position_jitter(width = 0, height = .05))
suppressWarnings(print(log10_scr_mean_amplitude_rain))
log10_scr_mean_amplitude_afex_plot <-
afex_plot(
log10_scr_mean_amplitude_rep_anova,
x = "Task",
trace = "Group",
error = "between",
error_arg = list(width = .15),
dodge = -.5,
mapping = c("color"),
point_arg = list(size = 4)
)Warning: Panel(s) show a mixed within-between-design.
Error bars do not allow comparisons across all means.
Suppress error bars with: error = "none"
Anova Table (Type 3 tests)
Response: log10_scr_mean_amplitude
Effect df MSE F ges p.value
1 Group 1, 92 1.44 0.48 .004 .491
2 Task 1.74, 160.43 0.27 14.04 *** .036 <.001
3 Group:Task 1.74, 160.43 0.27 0.35 <.001 .672
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘+’ 0.1 ‘ ’ 1
Sphericity correction method: GG $emmeans
Task emmean SE df lower.CL upper.CL
Unpleasant -4.31 0.0745 92 -4.45 -4.16
Neutral -4.68 0.0884 92 -4.85 -4.50
Pleasant -4.49 0.0831 92 -4.66 -4.33
Results are averaged over the levels of: Group
Confidence level used: 0.95
$contrasts
contrast estimate SE df t.ratio p.value
Unpleasant - Neutral 0.372 0.0733 92 5.075 <.0001
Unpleasant - Pleasant 0.187 0.0558 92 3.351 0.0033
Neutral - Pleasant -0.185 0.0793 92 -2.331 0.0564
Results are averaged over the levels of: Group
P value adjustment: tukey method for comparing a family of 3 estimates
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