# library(XML) opts_knit$set(upload.fun = imgur_upload)
library(reshape2)
library(ggplot2)
setwd("/Users/ruben/Dropbox/Self-Insight/ErsteErgebnisse/EMGplots")
load(file = "tetris.rdata")
WEIT = melt(tetris3[, c("vp", "event", "rl", "bh", "muscle", "ctime10", "activity")],
id.vars = c("vp", "event", "rl", "bh", "muscle", "ctime10"))
WEIT2 = dcast(WEIT, vp + rl + bh + event + muscle ~ ., fun.aggregate = mean)
names(WEIT2) = c("vp", "rl", "bh", "event", "muscle", "activity")
p = ggplot(data = WEIT2) + geom_jitter(shape = 1, alpha = 0.1) + scale_shape(solid = F) +
stat_summary(fun.data = "mean_cl_boot", geom = "smooth") + scale_y_continuous(limits = c(-1,
10))
p + aes(rl, activity) + scale_x_continuous("Rows deleted")
## Warning: Removed 2 rows containing missing values (stat_summary).
## Warning: Removed 2 rows containing missing values (geom_point).
p + aes(rl, activity) + facet_wrap(~muscle) + scale_x_continuous("Rows deleted")
## Warning: Removed 2 rows containing missing values (stat_summary).
## Warning: Removed 2 rows containing missing values (geom_point).
p + aes(bh, activity) + facet_wrap(~muscle) + scale_x_continuous("Black holes")
## Warning: Removed 2 rows containing missing values (stat_summary).
## Warning: Removed 2 rows containing missing values (geom_point).
p + aes(bh, activity) + facet_wrap(~rl) + scale_x_continuous(limits = c(0, 17)) +
scale_x_continuous("Black holes")
## Scale for 'x' is already present. Adding another scale for 'x', which will
## replace the existing scale.
## Warning: Removed 2 rows containing missing values (stat_summary).
## Warning: Removed 2 rows containing missing values (geom_point).
p + aes(bh, activity) + facet_wrap(~event + muscle) + scale_x_continuous(limits = c(0,
17)) + scale_x_continuous("Black holes")
## Scale for 'x' is already present. Adding another scale for 'x', which will
## replace the existing scale.
## Warning: Removed 2 rows containing missing values (stat_summary).
## Warning: Removed 2 rows containing missing values (geom_point).
## geom_path: Each group consist of only one observation. Do you need to
## adjust the group aesthetic?
## geom_path: Each group consist of only one observation. Do you need to
## adjust the group aesthetic?
## geom_path: Each group consist of only one observation. Do you need to
## adjust the group aesthetic?
## geom_path: Each group consist of only one observation. Do you need to
## adjust the group aesthetic?
qplot(event, activity, data = WEIT2, geom = "blank") + geom_boxplot() + facet_wrap(~muscle)
WEIT$firsthalf = WEIT$ctime10 <= 258
WEIT3 = dcast(WEIT, vp ~ event + muscle, fun.aggregate = mean)
library(ellipse)
correl = round(cor(WEIT3[, -1], use = "na.or.complete", method = "spearman"),
2)
correl
## baseline_corr baseline_zygo big.failure_corr
## baseline_corr 1.00 -0.14 0.25
## baseline_zygo -0.14 1.00 -0.03
## big.failure_corr 0.25 -0.03 1.00
## big.failure_zygo -0.01 0.05 -0.39
## gameover_corr 0.15 0.01 0.57
## gameover_zygo -0.14 0.02 -0.26
## small.failure_corr 0.05 -0.02 0.56
## small.failure_zygo -0.08 0.05 -0.32
## success_corr 0.04 0.00 0.42
## success_zygo -0.01 -0.07 -0.04
## big.failure_zygo gameover_corr gameover_zygo
## baseline_corr -0.01 0.15 -0.14
## baseline_zygo 0.05 0.01 0.02
## big.failure_corr -0.39 0.57 -0.26
## big.failure_zygo 1.00 -0.17 0.55
## gameover_corr -0.17 1.00 -0.31
## gameover_zygo 0.55 -0.31 1.00
## small.failure_corr -0.07 0.59 -0.07
## small.failure_zygo 0.48 -0.16 0.51
## success_corr -0.03 0.53 -0.04
## success_zygo 0.04 -0.13 0.33
## small.failure_corr small.failure_zygo success_corr
## baseline_corr 0.05 -0.08 0.04
## baseline_zygo -0.02 0.05 0.00
## big.failure_corr 0.56 -0.32 0.42
## big.failure_zygo -0.07 0.48 -0.03
## gameover_corr 0.59 -0.16 0.53
## gameover_zygo -0.07 0.51 -0.04
## small.failure_corr 1.00 -0.22 0.89
## small.failure_zygo -0.22 1.00 -0.18
## success_corr 0.89 -0.18 1.00
## success_zygo -0.20 0.54 -0.22
## success_zygo
## baseline_corr -0.01
## baseline_zygo -0.07
## big.failure_corr -0.04
## big.failure_zygo 0.04
## gameover_corr -0.13
## gameover_zygo 0.33
## small.failure_corr -0.20
## small.failure_zygo 0.54
## success_corr -0.22
## success_zygo 1.00
colorfun <- colorRamp(c("#CC0000", "white", "#3366CC"), space = "Lab")
plotcorr(correl, type = "upper", col = rgb(colorfun((correl + 1)/2), maxColorValue = 255))
write.table(WEIT3, dec = ",", "tetrisEMGweit3.csv", sep = "\t", qmethod = "double",
na = "99", row.names = F)
save(WEIT3, file = "tetrisWEIT3.RData")
gc()
## used (Mb) gc trigger (Mb) max used (Mb)
## Ncells 551241 29.5 899071 48.1 899071 48.1
## Vcells 4836119 36.9 13805511 105.4 13805336 105.4
library(psych)
## Attaching package: 'psych'
## The following object(s) are masked from 'package:Hmisc':
##
## describe
## The following object(s) are masked from 'package:ggplot2':
##
## %+%
number.of.factors = fa.parallel(correl, n.obs = nrow(WEIT3))
## Loading required package: MASS
## Parallel analysis suggests that the number of factors = 3 and the number of components = 3
fa(correl, n.obs = nrow(WEIT3), number.of.factors$nfact)
## Loading required package: GPArotation
## Factor Analysis using method = minres
## Call: fa(r = correl, nfactors = number.of.factors$nfact, n.obs = nrow(WEIT3))
## Standardized loadings (pattern matrix) based upon correlation matrix
## MR1 MR2 MR3 h2 u2
## baseline_corr 0.03 -0.18 0.05 0.034 0.966
## baseline_zygo -0.02 0.08 -0.08 0.011 0.989
## big.failure_corr 0.51 -0.50 0.19 0.574 0.426
## big.failure_zygo 0.06 0.79 -0.06 0.598 0.402
## gameover_corr 0.56 -0.27 0.07 0.430 0.570
## gameover_zygo 0.08 0.65 0.26 0.548 0.452
## small.failure_corr 1.00 0.03 -0.02 0.988 0.012
## small.failure_zygo -0.05 0.50 0.51 0.640 0.360
## success_corr 0.90 0.10 -0.08 0.808 0.192
## success_zygo -0.07 -0.02 0.84 0.713 0.287
##
## MR1 MR2 MR3
## SS loadings 2.44 1.77 1.14
## Proportion Var 0.24 0.18 0.11
## Cumulative Var 0.24 0.42 0.53
## Proportion Explained 0.46 0.33 0.21
## Cumulative Proportion 0.46 0.79 1.00
##
## With factor correlations of
## MR1 MR2 MR3
## MR1 1.00 -0.19 -0.14
## MR2 -0.19 1.00 0.22
## MR3 -0.14 0.22 1.00
##
## Test of the hypothesis that 3 factors are sufficient.
##
## The degrees of freedom for the null model are 45 and the objective function was 4.4 with Chi Square of 917.9
## The degrees of freedom for the model are 18 and the objective function was 0.39
##
## The root mean square of the residuals (RMSR) is 0.03
## The df corrected root mean square of the residuals is 0.08
## The number of observations was 214 with Chi Square = 81.4 with prob < 4.9e-10
##
## Tucker Lewis Index of factoring reliability = 0.817
## RMSEA index = 0.131 and the 90 % confidence intervals are 0.101 0.157
## BIC = -15.18
## Fit based upon off diagonal values = 0.97
## Measures of factor score adequacy
## MR1 MR2 MR3
## Correlation of scores with factors 0.99 0.90 0.88
## Multiple R square of scores with factors 0.99 0.80 0.77
## Minimum correlation of possible factor scores 0.98 0.61 0.55
fa(correl, n.obs = nrow(WEIT3), number.of.factors$nfact, rotate = "varimax")
## Factor Analysis using method = minres
## Call: fa(r = correl, nfactors = number.of.factors$nfact, n.obs = nrow(WEIT3),
## rotate = "varimax")
## Standardized loadings (pattern matrix) based upon correlation matrix
## MR1 MR2 MR3 h2 u2
## baseline_corr 0.04 -0.03 -0.18 0.034 0.966
## baseline_zygo -0.02 -0.04 0.09 0.011 0.989
## big.failure_corr 0.53 -0.06 -0.54 0.574 0.426
## big.failure_zygo -0.01 0.27 0.73 0.598 0.402
## gameover_corr 0.57 -0.09 -0.30 0.430 0.570
## gameover_zygo 0.00 0.52 0.53 0.548 0.452
## small.failure_corr 0.99 -0.08 -0.05 0.988 0.012
## small.failure_zygo -0.14 0.71 0.34 0.640 0.360
## success_corr 0.89 -0.11 0.04 0.808 0.192
## success_zygo -0.14 0.81 -0.19 0.713 0.287
##
## MR1 MR2 MR3
## SS loadings 2.43 1.53 1.39
## Proportion Var 0.24 0.15 0.14
## Cumulative Var 0.24 0.40 0.53
## Proportion Explained 0.45 0.29 0.26
## Cumulative Proportion 0.45 0.74 1.00
##
## Test of the hypothesis that 3 factors are sufficient.
##
## The degrees of freedom for the null model are 45 and the objective function was 4.4 with Chi Square of 917.9
## The degrees of freedom for the model are 18 and the objective function was 0.39
##
## The root mean square of the residuals (RMSR) is 0.03
## The df corrected root mean square of the residuals is 0.08
## The number of observations was 214 with Chi Square = 81.4 with prob < 4.9e-10
##
## Tucker Lewis Index of factoring reliability = 0.817
## RMSEA index = 0.131 and the 90 % confidence intervals are 0.101 0.157
## BIC = -15.18
## Fit based upon off diagonal values = 0.97
## Measures of factor score adequacy
## MR1 MR2 MR3
## Correlation of scores with factors 0.99 0.89 0.86
## Multiple R square of scores with factors 0.99 0.80 0.75
## Minimum correlation of possible factor scores 0.97 0.59 0.49
LANG = WEIT
LANG[which(LANG$event == "big.failure" | LANG$event == "small.failure"), "event"] = "failure"
breit = dcast(LANG, vp ~ event + muscle, fun.aggregate = mean)
(efa = fa(WEIT3[, -c(1:3)], fa.parallel(breit[, -1])$nfact, rotate = "varimax",
missing = T, fm = "ml"))
## Parallel analysis suggests that the number of factors = 3 and the number of components = 3
## Factor Analysis using method = ml
## Call: fa(r = WEIT3[, -c(1:3)], nfactors = fa.parallel(breit[, -1])$nfact,
## rotate = "varimax", missing = T, fm = "ml")
## Standardized loadings (pattern matrix) based upon correlation matrix
## ML3 ML2 ML1 h2 u2
## big.failure_corr 0.18 -0.18 0.96 1.00 0.005
## big.failure_zygo 0.05 0.53 -0.14 0.30 0.701
## gameover_corr 0.16 -0.12 0.58 0.38 0.624
## gameover_zygo 0.11 0.42 -0.24 0.25 0.754
## small.failure_corr 0.94 -0.11 0.30 1.00 0.005
## small.failure_zygo -0.14 0.99 -0.04 1.00 0.005
## success_corr 0.90 -0.01 0.09 0.82 0.180
## success_zygo -0.17 0.45 -0.03 0.24 0.763
##
## ML3 ML2 ML1
## SS loadings 1.82 1.69 1.45
## Proportion Var 0.23 0.21 0.18
## Cumulative Var 0.23 0.44 0.62
## Proportion Explained 0.37 0.34 0.29
## Cumulative Proportion 0.37 0.71 1.00
##
## Test of the hypothesis that 3 factors are sufficient.
##
## The degrees of freedom for the null model are 28 and the objective function was 3.82 with Chi Square of 800.3
## The degrees of freedom for the model are 7 and the objective function was 0.41
##
## The root mean square of the residuals (RMSR) is 0.04
## The df corrected root mean square of the residuals is 0.12
## The number of observations was 214 with Chi Square = 85.71 with prob < 9.4e-16
##
## Tucker Lewis Index of factoring reliability = 0.588
## RMSEA index = 0.233 and the 90 % confidence intervals are 0.187 0.274
## BIC = 48.15
## Fit based upon off diagonal values = 0.97
## Measures of factor score adequacy
## ML3 ML2 ML1
## Correlation of scores with factors 1.00 1.00 1.00
## Multiple R square of scores with factors 0.99 0.99 0.99
## Minimum correlation of possible factor scores 0.99 0.99 0.99
(efa = fa(breit[, -c(1:3)], number.of.factors$nfact, rotate = "varimax", missing = T,
fm = "ml"))
## In fa, too many factors requested for this number of variables to use SMC
## for communality estimates, 1s are used instead
## Factor Analysis using method = ml
## Call: fa(r = breit[, -c(1:3)], nfactors = number.of.factors$nfact,
## rotate = "varimax", missing = T, fm = "ml")
## Standardized loadings (pattern matrix) based upon correlation matrix
## ML1 ML2 ML3 h2 u2
## failure_corr 0.99 -0.08 -0.10 1.00 0.005
## failure_zygo -0.17 0.34 0.58 0.47 0.527
## gameover_corr 0.31 -0.02 -0.28 0.18 0.822
## gameover_zygo 0.05 0.05 0.72 0.52 0.478
## success_corr 0.88 -0.14 0.04 0.79 0.211
## success_zygo -0.12 0.97 0.19 1.00 0.005
##
## ML1 ML2 ML3
## SS loadings 1.89 1.09 0.97
## Proportion Var 0.32 0.18 0.16
## Cumulative Var 0.32 0.50 0.66
## Proportion Explained 0.48 0.28 0.25
## Cumulative Proportion 0.48 0.75 1.00
##
## Test of the hypothesis that 3 factors are sufficient.
##
## The degrees of freedom for the null model are 15 and the objective function was 2.22 with Chi Square of 465.7
## The degrees of freedom for the model are 0 and the objective function was 0.02
##
## The root mean square of the residuals (RMSR) is 0.01
## The number of observations was 214 with Chi Square = 5.05 with prob < NA
##
## Tucker Lewis Index of factoring reliability = -Inf
## Fit based upon off diagonal values = 1
## Measures of factor score adequacy
## ML1 ML2 ML3
## Correlation of scores with factors 1.00 0.99 0.80
## Multiple R square of scores with factors 0.99 0.98 0.63
## Minimum correlation of possible factor scores 0.99 0.96 0.27
efa = fa(breit[, -1], number.of.factors$nfact, rotate = "varimax")
efa$scores
## MR1 MR2 MR3
## 1 -0.48514 -0.8141212 -0.136979
## 2 0.51489 0.7337515 -0.402441
## 3 0.88641 0.0975498 2.727202
## 4 1.09178 -0.9464929 -0.054957
## 5 -1.49530 0.6477726 0.596305
## 6 -0.12004 -0.4686060 -0.272917
## 7 0.58889 1.6287194 1.851453
## 8 -0.60664 -0.3985989 0.019033
## 9 -0.59792 -0.5386740 -1.636100
## 10 1.61993 -0.9950512 1.903714
## 11 NaN NaN NaN
## 12 0.02901 -1.1176846 1.357861
## 13 NaN NaN NaN
## 14 0.09695 1.1512387 0.692658
## 15 0.75236 -0.3598299 -0.623129
## 16 -0.27225 -0.6707211 -0.139202
## 17 1.51353 0.0965476 0.209184
## 18 -0.83120 0.0332471 0.537109
## 19 -0.34129 -0.7387664 -0.010945
## 20 -0.18791 -0.4555252 0.138496
## 21 -1.68633 -0.1945235 0.411998
## 22 -0.30897 -0.0002259 -0.118250
## 23 1.94149 0.7254919 0.806063
## 24 -0.25610 -0.0965505 -0.135638
## 25 NaN NaN NaN
## 26 0.92916 0.2297771 1.316258
## 27 0.47172 -0.0583471 -1.131307
## 28 0.55128 -0.1375546 -0.483411
## 29 -1.96844 1.7216414 1.343886
## 30 1.55652 -0.4060185 1.306102
## 31 -0.96811 -0.2899665 -0.395953
## 32 0.09896 -0.4774857 -0.535379
## 33 NaN NaN NaN
## 34 -1.42227 -0.9948465 -0.538709
## 35 0.45629 -0.6002482 0.444528
## 36 0.92407 -0.0108851 -0.840229
## 37 -1.59105 1.8914059 0.911506
## 38 NaN NaN NaN
## 39 -2.45662 0.6558711 0.390377
## 40 -0.25517 0.4545269 -1.121986
## 41 -1.28977 -0.7450220 0.131493
## 42 0.45890 1.1031617 0.678390
## 43 2.55586 0.2975132 -0.624604
## 44 1.09826 -0.4540412 -0.136577
## 45 1.30385 0.1377728 -1.166338
## 46 -0.49631 1.3883597 1.083390
## 47 -0.55836 -0.4731540 -0.130348
## 48 -1.48670 -0.5809274 -0.763924
## 49 0.50380 -0.8520061 0.243985
## 50 0.15924 -0.5145480 -0.544016
## 51 -1.23695 -0.7935643 0.243645
## 52 -0.19139 2.0166547 1.988318
## 53 NaN NaN NaN
## 54 -0.13638 0.2233415 0.742785
## 55 0.92034 2.2880022 -2.305502
## 56 0.01086 -0.4390838 -0.142304
## 57 0.61914 -0.4476803 -0.124990
## 58 -0.24882 -0.7231133 -0.339538
## 59 -0.24121 -0.9631771 -0.448566
## 60 -1.34265 -0.8759436 0.011291
## 61 0.38681 -0.6941534 -0.197208
## 62 -0.82022 0.8392369 -1.175433
## 63 -0.03692 2.0347200 -0.814682
## 64 -0.31185 -0.5531945 -0.350470
## 65 1.32443 -0.2880045 0.017906
## 66 -0.64294 -0.0413378 -0.155505
## 67 -0.07785 -0.0627645 0.771992
## 68 -0.21285 -0.5533711 -0.784454
## 69 -1.56849 -0.7988623 -0.211406
## 70 NaN NaN NaN
## 71 -0.59683 -0.0349752 -0.169657
## 72 -0.13432 -0.0329477 -0.938224
## 73 -0.62467 -0.9060083 0.101466
## 74 0.26998 -0.2332967 -0.894763
## 75 -0.49544 -0.5222756 -0.186107
## 76 NaN NaN NaN
## 77 -0.27419 -0.3673303 -0.735896
## 78 NaN NaN NaN
## 79 -0.69747 0.9239488 -0.669921
## 80 0.70003 0.6953384 0.400827
## 81 -0.14859 0.5415966 0.887178
## 82 -0.14361 -0.2830238 -0.005984
## 83 -0.46244 -0.0913998 -0.151241
## 84 0.90521 -0.4663279 0.037747
## 85 -0.03548 0.4426770 0.044141
## 86 -1.70451 0.9833780 -0.833995
## 87 0.40557 -0.0077008 -0.048200
## 88 -1.37115 -0.6003726 -0.299604
## 89 1.37031 -1.0150151 -0.244517
## 90 1.21353 0.6978033 -0.087715
## 91 0.36577 -0.8458237 0.049453
## 92 -0.82522 -0.5175249 -0.479357
## 93 -1.22279 0.4867173 -0.756023
## 94 NaN NaN NaN
## 95 -0.54922 3.1943973 -0.043212
## 96 -0.48080 0.4861953 1.285630
## 97 -0.77095 -0.5180137 -0.781917
## 98 NaN NaN NaN
## 99 -0.13263 -0.4033884 -0.229204
## 100 1.22847 0.1000521 0.299217
## 101 0.95397 -0.4770846 -0.228678
## 102 -1.13201 0.3610960 0.259445
## 103 0.07041 -0.6849297 -0.001797
## 104 -0.76058 2.9527968 -0.258727
## 105 2.19813 2.6061822 -0.641452
## 106 -0.12373 2.9869675 0.475728
## 107 1.47100 0.2311962 -1.486037
## 108 NaN NaN NaN
## 109 -0.50593 1.1737209 2.311369
## 110 1.19946 -1.4109341 1.317629
## 111 -0.12978 0.0436242 0.471915
## 112 NaN NaN NaN
## 113 1.24377 2.0238728 -1.756002
## 114 1.64402 -0.4208370 0.277422
## 115 -0.47266 0.8957078 0.513682
## 116 1.34283 -0.5993755 0.080409
## 117 0.28268 -0.4280437 0.302890
## 118 0.31716 -0.4145794 0.531401
## 119 1.95927 -0.8590215 1.480213
## 120 -0.23441 -0.2931578 -0.032692
## 121 0.72110 0.1462545 0.101557
## 122 0.27453 2.0335599 -0.814131
## 123 -1.70461 -0.0435545 -0.781074
## 124 0.66492 -0.2206197 -0.408356
## 125 -0.08066 -0.9841873 -0.024083
## 126 0.60984 -0.5316965 0.270318
## 127 -0.82429 1.2512140 -1.017522
## 128 -1.23299 -0.6770361 -0.014617
## 129 0.37628 -0.1062939 0.026186
## 130 -2.21530 1.8360794 1.212368
## 131 -1.15909 -0.9441270 -0.067188
## 132 NaN NaN NaN
## 133 NaN NaN NaN
## 134 -0.06349 0.5450359 1.250196
## 135 0.49417 -1.9502933 0.790221
## 136 -0.10122 1.0949605 -0.053435
## 137 -0.22171 -0.8259696 -0.884904
## 138 0.08812 -0.5013169 -0.031659
## 139 -1.14259 0.0760303 0.180839
## 140 0.32265 0.8255711 -0.954939
## 141 -0.29220 0.5689290 0.163304
## 142 0.80119 0.2327859 -0.637041
## 143 -0.23234 -0.8014117 -0.185760
## 144 -1.00702 0.6838489 0.197624
## 145 0.30699 0.3681743 0.669983
## 146 -0.85008 -0.7613478 0.327889
## 147 1.82360 0.1651609 -0.276380
## 148 0.01081 -0.5296350 0.527765
## 149 NaN NaN NaN
## 150 0.55323 0.9442904 -0.999393
## 151 -0.73613 0.2171196 0.177403
## 152 1.53641 0.9808048 -0.233117
## 153 NaN NaN NaN
## 154 -0.82711 1.1644084 1.167121
## 155 1.64931 0.6252002 0.402468
## 156 -0.36778 1.3729775 1.342395
## 157 NaN NaN NaN
## 158 -0.03987 -0.0963102 -0.692296
## 159 -1.26570 1.0876267 0.526447
## 160 0.85169 0.0706372 -0.590268
## 161 -1.57365 1.0228353 -0.685048
## 162 -0.65744 -0.8001068 -0.121657
## 163 0.11249 -0.3323173 0.512700
## 164 1.47962 0.2964149 -0.835490
## 165 -1.77011 0.4547862 -0.295922
## 166 -0.46943 -0.5877175 -0.082177
## 167 1.60723 -0.3129723 0.146218
## 168 -0.45147 -1.1500194 -0.272064
## 169 2.09783 -0.7533014 -0.146530
## 170 NaN NaN NaN
## 171 0.62900 -0.5993592 0.263793
## 172 0.24800 -0.3370904 -0.231498
## 173 0.56302 -0.7933837 0.420861
## 174 0.93227 0.7276840 0.361351
## 175 -0.68262 -0.6036964 -0.238755
## 176 -0.95162 0.9377103 1.122475
## 177 0.36978 -0.4233363 0.178553
## 178 -0.77447 0.3864033 0.381552
## 179 -0.63488 -0.6973837 -0.691383
## 180 1.17509 1.0396341 -0.095057
## 181 0.04336 -0.9883300 0.724023
## 182 0.14643 -0.3936881 0.413178
## 183 -0.98760 -0.3856323 0.089400
## 184 -1.12891 -0.5648768 -1.053435
## 185 -0.91959 -0.0244296 -1.337478
## 186 0.64598 -0.4662473 0.238344
## 187 0.09554 -0.4913583 0.573988
## 188 -0.53819 -0.3346968 -0.091174
## 189 0.77260 -0.3448231 -0.588491
## 190 NaN NaN NaN
## 191 -0.37600 -0.7227575 -0.209818
## 192 NaN NaN NaN
## 193 0.12663 0.0184960 0.187831
## 194 -0.77157 -0.8432080 -0.872974
## 195 1.56865 -0.1714596 0.430326
## 196 0.06355 -0.1423476 -0.072167
## 197 -0.55221 -0.6342822 -0.225320
## 198 -0.96667 -0.4587200 -0.173537
## 199 -0.39307 1.5244100 -0.472477
## 200 NaN NaN NaN
## 201 -0.90262 -0.7341547 -0.782507
## 202 0.03241 -0.4988132 -0.089957
## 203 -1.57793 -1.1353281 0.074743
## 204 0.94646 -0.2547730 -0.152031
## 205 2.40228 -1.0015664 0.479403
## 206 2.00434 0.1016919 -0.770253
## 207 -0.87912 1.9662760 1.975026
## 208 -1.52010 -0.3932592 -0.490710
## 209 -0.58470 0.5553851 -0.928376
## 210 0.07929 -0.1141344 -0.515964
## 211 2.63915 1.7505692 -2.477876
## 212 -1.33527 -0.2395151 -0.404214
## 213 0.21974 -0.2722001 -0.847377
## 214 -1.23369 -1.0474969 -0.039905
summary(fakt)
## Error: object 'fakt' not found
WEIT$odd = (WEIT$ctime10%%8) %nin% c(0, 1, 2, 3)
WEIT4 = dcast(WEIT, vp ~ event + muscle + odd, fun.aggregate = mean)
correl = round(cor(WEIT4[, 2:8], use = "na.or.complete", method = "spearman"),
2)
correl
## baseline_corr_FALSE baseline_corr_TRUE
## baseline_corr_FALSE 1.00 0.91
## baseline_corr_TRUE 0.91 1.00
## baseline_zygo_FALSE -0.11 -0.14
## baseline_zygo_TRUE -0.14 -0.15
## big.failure_corr_FALSE 0.20 0.24
## big.failure_corr_TRUE 0.21 0.15
## big.failure_zygo_FALSE -0.01 0.04
## baseline_zygo_FALSE baseline_zygo_TRUE
## baseline_corr_FALSE -0.11 -0.14
## baseline_corr_TRUE -0.14 -0.15
## baseline_zygo_FALSE 1.00 0.88
## baseline_zygo_TRUE 0.88 1.00
## big.failure_corr_FALSE 0.01 0.01
## big.failure_corr_TRUE -0.06 -0.08
## big.failure_zygo_FALSE -0.02 0.01
## big.failure_corr_FALSE big.failure_corr_TRUE
## baseline_corr_FALSE 0.20 0.21
## baseline_corr_TRUE 0.24 0.15
## baseline_zygo_FALSE 0.01 -0.06
## baseline_zygo_TRUE 0.01 -0.08
## big.failure_corr_FALSE 1.00 0.84
## big.failure_corr_TRUE 0.84 1.00
## big.failure_zygo_FALSE -0.34 -0.45
## big.failure_zygo_FALSE
## baseline_corr_FALSE -0.01
## baseline_corr_TRUE 0.04
## baseline_zygo_FALSE -0.02
## baseline_zygo_TRUE 0.01
## big.failure_corr_FALSE -0.34
## big.failure_corr_TRUE -0.45
## big.failure_zygo_FALSE 1.00
Yields extremely high positive correlations, but that might just be due to closeness in time / autocorrelation?.
library(lme4)
## Loading required package: lattice
## Loading required package: Matrix
tetris3$event = as.factor(tetris3$event)
### simple icc
lmer(activity ~ (1 |vp),data=tetris3) # not much variance explained by the person
## Linear mixed model fit by REML ['lmerMod']
## Formula: activity ~ (1 | vp)
## Data: tetris3
##
## REML criterion at convergence: 539975
##
## Random effects:
## Groups Name Variance Std.Dev.
## vp (Intercept) 0.024 0.155
## Residual 0.558 0.747
## Number of obs: 239095, groups: vp, 214
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 0.0609 0.0107 5.69
tetris4 = melt(tetris3,measure.vars="activity")
tetris4 = dcast(tetris4,... ~ muscle)
head(tetris4)
## evnumber vp ctime10 event rl bh variable corr zygo
## 1 51 101 0 baseline 0 0 activity 0.4400 -0.13426
## 2 51 101 1 baseline 0 0 activity 0.3190 -0.15062
## 3 51 101 2 baseline 0 0 activity 0.5768 -0.15681
## 4 51 101 3 baseline 0 0 activity 0.3806 -0.15254
## 5 51 101 4 baseline 0 0 activity 0.3623 -0.14697
## 6 51 101 5 baseline 0 0 activity 0.2842 -0.09246
source(file="~/R/self-insight/diary/2- jaap instruction - snippet calculate slope reliability.R")
(iislopes.z = lmer(zygo ~ rl + bh + ctime10 + (1 + rl + bh + ctime10|vp),data=tetris4))
## Linear mixed model fit by REML ['lmerMod']
## Formula: zygo ~ rl + bh + ctime10 + (1 + rl + bh + ctime10 | vp)
## Data: tetris4
##
## REML criterion at convergence: 303558
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## vp (Intercept) 0.201596 0.4490
## rl 0.294234 0.5424 0.691
## bh 2.267695 1.5059 0.681 0.931
## ctime10 0.000111 0.0105 -0.764 -0.958 -0.985
## Residual 0.717849 0.8473
## Number of obs: 119552, groups: vp, 214
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 0.006259 0.031195 0.20
## rl -0.106968 0.037420 -2.86
## bh 0.033877 0.102962 0.33
## ctime10 0.000137 0.000720 0.19
##
## Correlation of Fixed Effects:
## (Intr) rl bh
## rl 0.668
## bh 0.670 0.923
## ctime10 -0.755 -0.949 -0.984
summary(tetris4)
## evnumber vp ctime10 event
## Min. : 51 Min. :101 Min. : 0 baseline :13148
## 1st Qu.:184 1st Qu.:155 1st Qu.: 134 big.failure : 2813
## Median :217 Median :208 Median : 258 gameover : 3224
## Mean :194 Mean :208 Mean : 262 small.failure:69222
## 3rd Qu.:219 3rd Qu.:262 3rd Qu.: 379 success :31156
## Max. :245 Max. :320 Max. :1047
##
## rl bh variable corr
## Min. :0.00 Min. : 0.00 activity:119563 Min. :-1.195
## 1st Qu.:0.00 1st Qu.: 1.00 1st Qu.:-0.280
## Median :0.00 Median : 2.00 Median :-0.023
## Mean :0.33 Mean : 3.06 Mean : 0.029
## 3rd Qu.:1.00 3rd Qu.: 4.00 3rd Qu.: 0.255
## Max. :4.00 Max. :30.00 Max. :23.346
## NA's :20
## zygo
## Min. :-0.95
## 1st Qu.:-0.21
## Median :-0.13
## Mean : 0.09
## 3rd Qu.: 0.02
## Max. :33.68
## NA's :11
(iislopes.z2 = lmer(zygo ~ rl + bh + ctime10 + event + (1 + rl + bh + ctime10 + event|vp),data=tetris4))
## caught warning: failure to converge in 10000 evaluations
## Linear mixed model fit by REML ['lmerMod']
## Formula: zygo ~ rl + bh + ctime10 + event + (1 + rl + bh + ctime10 + event | vp)
## Data: tetris4
##
## REML criterion at convergence: 290325
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## vp (Intercept) 7.48e-01 0.86475
## rl 7.41e-02 0.27224 0.806
## bh 3.27e-02 0.18086 0.529 0.534
## ctime10 6.65e-06 0.00258 -0.716 -0.717 -0.320
## eventbig.failure 2.97e+00 1.72249 0.245 0.029 0.049 -0.079
## eventgameover 3.82e+00 1.95405 0.254 0.327 -0.115 -0.022
## eventsmall.failure 4.43e-01 0.66561 -0.378 -0.476 -0.221 -0.072
## eventsuccess 5.90e-01 0.76812 -0.572 -0.495 -0.376 0.250
## Residual 6.34e-01 0.79612
##
##
##
##
##
##
## 0.205
## 0.401 -0.140
## 0.210 -0.050 0.631
##
## Number of obs: 119552, groups: vp, 214
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 0.133601 0.059530 2.24
## rl 0.006857 0.021123 0.32
## bh 0.089026 0.012592 7.07
## ctime10 0.000196 0.000180 1.09
## eventbig.failure -0.058020 0.144085 -0.40
## eventgameover -1.301460 0.142986 -9.10
## eventsmall.failure -0.285777 0.046665 -6.12
## eventsuccess -0.352676 0.054989 -6.41
##
## Correlation of Fixed Effects:
## (Intr) rl bh ctim10 evntb. evntgm evnts.
## rl 0.706
## bh 0.517 0.466
## ctime10 -0.701 -0.624 -0.325
## eventbg.flr 0.194 0.009 0.024 -0.067
## eventgamevr 0.229 0.273 -0.139 -0.014 0.176
## evntsmll.fl -0.381 -0.409 -0.219 -0.088 0.340 -0.105
## eventsuccss -0.556 -0.521 -0.355 0.221 0.180 -0.033 0.620
relia.z = get.reliabilites(iislopes.z)
## Attaching package: 'plyr'
## The following object(s) are masked from 'package:Hmisc':
##
## is.discrete, summarize
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
relia.z2 = get.reliabilites(iislopes.z2)
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## Error: undefined columns selected
(iislopes.c = lmer(corr ~ rl + bh + (1 + rl + bh + ctime10 |vp) + ctime10,data=tetris4))
## Linear mixed model fit by REML ['lmerMod']
## Formula: corr ~ rl + bh + (1 + rl + bh + ctime10 | vp) + ctime10
## Data: tetris4
##
## REML criterion at convergence: 145611
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## vp (Intercept) 8.95e-02 0.29919
## rl 1.50e-01 0.38767 0.244
## bh 2.50e-01 0.50043 0.409 0.198
## ctime10 2.67e-05 0.00517 -0.478 -0.052 -0.969
## Residual 1.90e-01 0.43621
## Number of obs: 119543, groups: vp, 214
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) -0.037270 0.020657 -1.80
## rl 0.047468 0.026673 1.78
## bh -0.009961 0.034227 -0.29
## ctime10 0.000298 0.000353 0.84
##
## Correlation of Fixed Effects:
## (Intr) rl bh
## rl 0.237
## bh 0.405 0.197
## ctime10 -0.476 -0.053 -0.968
relia.c = get.reliabilites(iislopes.c)
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
tetris5 = na.omit(tetris4)
tetris5[,c("eventbig.failure", "eventgameover", "eventsmall.failure", "eventsuccess")]= model.matrix(zygo ~ event,tetris5)[,-1]
(iislopes.z.dummy = lmer(zygo ~ rl + bh + ctime10 + eventbig.failure + eventgameover + eventsmall.failure + eventsuccess + (1 + rl + bh + ctime10 + eventbig.failure + eventgameover + eventsmall.failure + eventsuccess|vp),data=tetris5))
## caught warning: failure to converge in 10000 evaluations
## Linear mixed model fit by REML ['lmerMod']
## Formula: zygo ~ rl + bh + ctime10 + eventbig.failure + eventgameover + eventsmall.failure + eventsuccess + (1 + rl + bh + ctime10 + eventbig.failure + eventgameover + eventsmall.failure + eventsuccess | vp)
## Data: tetris5
##
## REML criterion at convergence: 290406
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## vp (Intercept) 1.36e+00 1.1649
## rl 3.95e-02 0.1988 0.711
## bh 3.73e-02 0.1931 0.497 0.562
## ctime10 9.62e-06 0.0031 -0.838 -0.680 -0.353
## eventbig.failure 3.49e+00 1.8669 0.273 -0.074 0.046 -0.128
## eventgameover 3.76e+00 1.9398 0.269 0.270 -0.145 -0.109
## eventsmall.failure 4.97e-01 0.7053 -0.220 -0.385 -0.357 -0.092
## eventsuccess 4.85e-01 0.6964 -0.045 0.013 -0.178 -0.147
## Residual 6.33e-01 0.7957
##
##
##
##
##
##
## 0.184
## 0.410 -0.150
## 0.339 0.170 0.444
##
## Number of obs: 119532, groups: vp, 214
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 0.133573 0.079942 1.67
## rl -0.003587 0.017052 -0.21
## bh 0.089041 0.013424 6.63
## ctime10 0.000196 0.000215 0.91
## eventbig.failure 0.006914 0.158988 0.04
## eventgameover -1.306790 0.142014 -9.20
## eventsmall.failure -0.285738 0.049315 -5.79
## eventsuccess -0.341882 0.050415 -6.78
##
## Correlation of Fixed Effects:
## (Intr) rl bh ctim10 evntb. evntgm evnts.
## rl 0.564
## bh 0.488 0.444
## ctime10 -0.826 -0.537 -0.356
## eventbg.flr 0.214 -0.043 0.025 -0.103
## eventgamevr 0.246 0.201 -0.164 -0.096 0.157
## evntsmll.fl -0.225 -0.300 -0.350 -0.104 0.338 -0.115
## eventsuccss -0.054 -0.139 -0.167 -0.150 0.265 0.163 0.444
relia.z3 = get.reliabilites(iislopes.z.dummy)
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
(iislopes.z.subset = lmer(zygo ~ rl + bh + ctime10 + eventgameover + (1 + rl + bh + ctime10 + eventgameover |vp),data=tetris5))
## Linear mixed model fit by REML ['lmerMod']
## Formula: zygo ~ rl + bh + ctime10 + eventgameover + (1 + rl + bh + ctime10 + eventgameover | vp)
## Data: tetris5
##
## REML criterion at convergence: 295333
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## vp (Intercept) 9.31e-02 0.30505
## rl 4.14e-02 0.20337 -0.446
## bh 1.42e-01 0.37618 -0.494 0.470
## ctime10 2.11e-06 0.00145 -0.336 -0.358 -0.214
## eventgameover 4.05e+00 2.01266 -0.004 -0.124 -0.059 0.407
## Residual 6.70e-01 0.81868
## Number of obs: 119532, groups: vp, 214
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) -0.007346 0.021557 -0.34
## rl -0.078917 0.014762 -5.35
## bh 0.081366 0.025822 3.15
## ctime10 -0.000193 0.000104 -1.87
## eventgameover -0.984288 0.146894 -6.70
##
## Correlation of Fixed Effects:
## (Intr) rl bh ctim10
## rl -0.423
## bh -0.476 0.447
## ctime10 -0.354 -0.338 -0.220
## eventgamevr -0.002 -0.116 -0.067 0.385
relia.z4 = get.reliabilites(iislopes.z.subset)
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
(iislopes.c.subset = lmer(corr ~ rl + bh + ctime10 + eventgameover + (1 + rl + bh + ctime10 + eventgameover |vp),data=tetris5))
## Linear mixed model fit by REML ['lmerMod']
## Formula: corr ~ rl + bh + ctime10 + eventgameover + (1 + rl + bh + ctime10 + eventgameover | vp)
## Data: tetris5
##
## REML criterion at convergence: 142342
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## vp (Intercept) 4.10e-01 0.64005
## rl 6.80e-02 0.26067 0.772
## bh 7.69e-03 0.08771 0.507 0.602
## ctime10 4.25e-06 0.00206 -0.824 -0.633 -0.709
## eventgameover 5.23e-01 0.72294 0.583 0.693 0.301 -0.503
## Residual 1.86e-01 0.43095
## Number of obs: 119532, groups: vp, 214
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) -0.042353 0.043849 -0.97
## rl 0.041041 0.018028 2.28
## bh -0.012039 0.006102 -1.97
## ctime10 0.000336 0.000142 2.37
## eventgameover -0.012516 0.053038 -0.24
##
## Correlation of Fixed Effects:
## (Intr) rl bh ctim10
## rl 0.760
## bh 0.497 0.589
## ctime10 -0.821 -0.624 -0.705
## eventgamevr 0.543 0.635 0.245 -0.457
relia.c4 = get.reliabilites(iislopes.c.subset)
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust
## this.
sapply(relia.z4,mean) # mean of reliabilities ZYGO
## (Intercept) rl bh ctime10 eventgameover
## 0.006771 0.021436 0.058774 0.979738 0.005926
sapply(relia.c4,mean) # mean of reliabilities CORR
## (Intercept) rl bh ctime10 eventgameover
## 0.130364 0.041748 0.088193 0.973316 0.003303
library(QuantPsyc)
## Loading required package: boot
## Attaching package: 'boot'
## The following object(s) are masked from 'package:lattice':
##
## melanoma
## The following object(s) are masked from 'package:psych':
##
## logit
## The following object(s) are masked from 'package:survival':
##
## aml
## Attaching package: 'QuantPsyc'
## The following object(s) are masked from 'package:Matrix':
##
## norm
## The following object(s) are masked from 'package:base':
##
## norm
slopes.z = as.data.frame(Make.Z(coef(iislopes.z.subset)$vp))
slopes.z$vp = rownames(slopes.z)
qplot(value,vp,data=melt(slopes.z,id="vp"),geom="text",label=vp) + facet_wrap(~ variable)
slopes.c = as.data.frame(Make.Z(coef(iislopes.c.subset)$vp))
slopes.c$vp = rownames(slopes.c)
qplot(value,vp,data=melt(slopes.c,id="vp"),geom="text",label=vp) + facet_wrap(~ variable)
slopes = merge(slopes.z,slopes.c,by="vp",suffixes=c("_zygo","_corr"))
write.table(slopes, dec=",", "tetris_slopes.csv", sep="\t",qmethod="double",na="99",row.names=F)
gc()
## used (Mb) gc trigger (Mb) max used (Mb)
## Ncells 1534539 82.0 2403845 128.4 2251281 120.3
## Vcells 44844325 342.2 66300163 505.9 66258782 505.6
library(stringr)
ggplot(data=tetris3) +
scale_x_continuous(limits=c(0,583)) +
labs(title=str_c("Tetris")) +
stat_summary(aes(x=ctime10,y=activity,fill=muscle,alpha=0.2),geom="ribbon",fun.data="mean_sdl",mult=0.5)+
stat_summary(aes(x=ctime10,y=activity,colour=muscle),geom="line",fun.data="mean_sdl")+
scale_fill_manual(values=c("#DEDEDE","#31429C"))+
scale_colour_manual(values=c('#000000','#4184BE'))
## Warning: Removed 2360 rows containing missing values (stat_summary).
## Warning: Removed 2360 rows containing missing values (stat_summary).
ggplot(data=tetris3) +
scale_x_continuous(limits=c(0,583)) +
scale_y_continuous(limits=c(-1,12)) +
labs(title=str_c("Tetris")) +
geom_rect(aes(fill=as.factor(event),xmin = ctime10,xmax=ctime10+1,ymax=12,ymin=12-(rl*2)-(bh/2),alpha=.5)) +
scale_fill_manual(values=c("#ffffff","#b34c55","#723B51","#b95B6a","#80A55F"))+
geom_line(aes(x=ctime10,y=activity,colour=muscle))+
scale_colour_manual(values=c('#000000','#4184BE'))+
facet_wrap(~ vp)
## Warning: Removed 16 rows containing missing values (geom_path).
## Warning: Removed 32 rows containing missing values (geom_path).
## Warning: Removed 1122 rows containing missing values (geom_path).
## Warning: Removed 34 rows containing missing values (geom_path).
## Warning: Removed 60 rows containing missing values (geom_path).
## Warning: Removed 2 rows containing missing values (geom_path).
## Warning: Removed 40 rows containing missing values (geom_path).
## Warning: Removed 88 rows containing missing values (geom_path).
## Warning: Removed 1 rows containing missing values (geom_path).
## Warning: Removed 6 rows containing missing values (geom_path).
## Warning: Removed 1 rows containing missing values (geom_path).
## Warning: Removed 12 rows containing missing values (geom_path).
## Warning: Removed 1 rows containing missing values (geom_path).
## Warning: Removed 16 rows containing missing values (geom_path).
## Warning: Removed 60 rows containing missing values (geom_path).
## Warning: Removed 126 rows containing missing values (geom_path).
## Warning: Removed 136 rows containing missing values (geom_path).
## Warning: Removed 58 rows containing missing values (geom_path).
## Warning: Removed 56 rows containing missing values (geom_path).
## Warning: Removed 172 rows containing missing values (geom_path).
## Warning: Removed 1 rows containing missing values (geom_path).
## Warning: Removed 80 rows containing missing values (geom_path).
## Warning: Removed 140 rows containing missing values (geom_path).
## Warning: Removed 104 rows containing missing values (geom_path).
