{ "cells": [ { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "library(multilevel)\n", "library(lme4)\n", "library(ggplot2)\n", "library(multcomp)\n", "#library(sjPlot)\n", "require(StatisticalModels)\n", "library(devtools)\n", "library(car)\n", "library(mlr)\n", "library(ROSE)\n", "library (e1071)\n", "library(MLmetrics)\n", "library(caret)\n", "library(missForest)\n", "library(doParallel)\n", "library(ROCR)\n", "library(glmmLasso)\n", "library(effects)\n", "library(data.table)\n", "library(pROC)\n", "library(effects)\n", "library(tidyverse)\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Check the effect of task characteristics of the Spot-The-Difference task on trial level cheating" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\n", "
subX.xUnnamed..0Trial_NrStartLDurationLStartQDurationQNdiffResponse⋯ImageLevelRewardrunrampBalanceCheatingMagnitudeexpX.yCC
S111 0 1 2 74.203 2 84.026 3 1 2 ⋯ dirt1 hard 0.2 1 0 0.00 0 EEG 12 7
S111 1 2 3 91.531 2 101.567 3 2 2 ⋯ underwater2hard 0.2 1 0 0.00 0 EEG 12 7
S111 2 4 5 124.946 2 135.143 3 2 2 ⋯ grassy2 hard 0.2 1 0 0.05 0 EEG 12 7
S111 3 6 8 180.329 2 189.459 3 2 2 ⋯ libby2 veryhard 0.4 1 0 0.10 0 EEG 12 7
S111 4 10 12 251.319 2 261.729 3 2 1 ⋯ redriv2 hard 0.2 1 0 0.45 1 EEG 12 7
S111 5 13 15 302.969 2 313.486 3 2 2 ⋯ sunny2 veryhard 0.4 1 0 0.55 0 EEG 12 7
\n" ], "text/latex": [ "\\begin{tabular}{r|llllllllllllllllllllll}\n", " sub & X.x & Unnamed..0 & Trial\\_Nr & StartL & DurationL & StartQ & DurationQ & Ndiff & Response & ⋯ & Image & Level & Reward & run & ramp & Balance & CheatingMagnitude & exp & X.y & CC\\\\\n", "\\hline\n", "\t S111 & 0 & 1 & 2 & 74.203 & 2 & 84.026 & 3 & 1 & 2 & ⋯ & dirt1 & hard & 0.2 & 1 & 0 & 0.00 & 0 & EEG & 12 & 7 \\\\\n", "\t S111 & 1 & 2 & 3 & 91.531 & 2 & 101.567 & 3 & 2 & 2 & ⋯ & underwater2 & hard & 0.2 & 1 & 0 & 0.00 & 0 & EEG & 12 & 7 \\\\\n", "\t S111 & 2 & 4 & 5 & 124.946 & 2 & 135.143 & 3 & 2 & 2 & ⋯ & grassy2 & hard & 0.2 & 1 & 0 & 0.05 & 0 & EEG & 12 & 7 \\\\\n", "\t S111 & 3 & 6 & 8 & 180.329 & 2 & 189.459 & 3 & 2 & 2 & ⋯ & libby2 & veryhard & 0.4 & 1 & 0 & 0.10 & 0 & EEG & 12 & 7 \\\\\n", "\t S111 & 4 & 10 & 12 & 251.319 & 2 & 261.729 & 3 & 2 & 1 & ⋯ & redriv2 & hard & 0.2 & 1 & 0 & 0.45 & 1 & EEG & 12 & 7 \\\\\n", "\t S111 & 5 & 13 & 15 & 302.969 & 2 & 313.486 & 3 & 2 & 2 & ⋯ & sunny2 & veryhard & 0.4 & 1 & 0 & 0.55 & 0 & EEG & 12 & 7 \\\\\n", "\\end{tabular}\n" ], "text/markdown": [ "\n", "sub | X.x | Unnamed..0 | Trial_Nr | StartL | DurationL | StartQ | DurationQ | Ndiff | Response | ⋯ | Image | Level | Reward | run | ramp | Balance | CheatingMagnitude | exp | X.y | CC | \n", "|---|---|---|---|---|---|\n", "| S111 | 0 | 1 | 2 | 74.203 | 2 | 84.026 | 3 | 1 | 2 | ⋯ | dirt1 | hard | 0.2 | 1 | 0 | 0.00 | 0 | EEG | 12 | 7 | \n", "| S111 | 1 | 2 | 3 | 91.531 | 2 | 101.567 | 3 | 2 | 2 | ⋯ | underwater2 | hard | 0.2 | 1 | 0 | 0.00 | 0 | EEG | 12 | 7 | \n", "| S111 | 2 | 4 | 5 | 124.946 | 2 | 135.143 | 3 | 2 | 2 | ⋯ | grassy2 | hard | 0.2 | 1 | 0 | 0.05 | 0 | EEG | 12 | 7 | \n", "| S111 | 3 | 6 | 8 | 180.329 | 2 | 189.459 | 3 | 2 | 2 | ⋯ | libby2 | veryhard | 0.4 | 1 | 0 | 0.10 | 0 | EEG | 12 | 7 | \n", "| S111 | 4 | 10 | 12 | 251.319 | 2 | 261.729 | 3 | 2 | 1 | ⋯ | redriv2 | hard | 0.2 | 1 | 0 | 0.45 | 1 | EEG | 12 | 7 | \n", "| S111 | 5 | 13 | 15 | 302.969 | 2 | 313.486 | 3 | 2 | 2 | ⋯ | sunny2 | veryhard | 0.4 | 1 | 0 | 0.55 | 0 | EEG | 12 | 7 | \n", "\n", "\n" ], "text/plain": [ " sub X.x Unnamed..0 Trial_Nr StartL DurationL StartQ DurationQ Ndiff\n", "1 S111 0 1 2 74.203 2 84.026 3 1 \n", "2 S111 1 2 3 91.531 2 101.567 3 2 \n", "3 S111 2 4 5 124.946 2 135.143 3 2 \n", "4 S111 3 6 8 180.329 2 189.459 3 2 \n", "5 S111 4 10 12 251.319 2 261.729 3 2 \n", "6 S111 5 13 15 302.969 2 313.486 3 2 \n", " Response ⋯ Image Level Reward run ramp Balance CheatingMagnitude exp\n", "1 2 ⋯ dirt1 hard 0.2 1 0 0.00 0 EEG\n", "2 2 ⋯ underwater2 hard 0.2 1 0 0.00 0 EEG\n", "3 2 ⋯ grassy2 hard 0.2 1 0 0.05 0 EEG\n", "4 2 ⋯ libby2 veryhard 0.4 1 0 0.10 0 EEG\n", "5 1 ⋯ redriv2 hard 0.2 1 0 0.45 1 EEG\n", "6 2 ⋯ sunny2 veryhard 0.4 1 0 0.55 0 EEG\n", " X.y CC\n", "1 12 7 \n", "2 12 7 \n", "3 12 7 \n", "4 12 7 \n", "5 12 7 \n", "6 12 7 " ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [ "\n", " -2.4107574626396 -0.957046730130456 0.981234246548403 \n", " 29 1146 1189 " ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# Load Data\n", "SPD=read.csv('/data/sebastian/EEG/Behavioral/SPD-EEG-repo.csv')\n", "\n", "# remove non-cheatable trials\n", "data = SPD[which(SPD$Ndiff < 3),]\n", "\n", "# load the cheatcount file\n", "CC_all=read.csv('/data/sebastian/EEG/Behavioral/CC_all_repo.csv')\n", "colnames(CC_all)[3]<-'CC'\n", "\n", "# merge Cheatcount and TbT data\n", "mC<-merge(data,CC_all,by=\"sub\", sort = F)\n", "head(mC)\n", "\n", "# remove unneeded columns\n", "mC_c<- mC[ , -which(names(mC) %in% c(\"Image\",\"gender\",\"ImageName\",\"Level\",'X.x','X.y','exp','Unnamed..0'))]\n", "\n", "# remove Cheated\n", "subset<-subset(mC_c, select=-c(Cheat,sub))\n", "\n", "subset$RT_log<- log(subset$RT)\n", "\n", "# scale the data\n", "mCsd<-as.data.frame(scale(subset))\n", "mCsd$Cheated<-mC$Cheat\n", "mCsd$sub<-as.factor(mC$sub)\n", "\n", "# remove non-cheatable trials\n", "data = mCsd[which(mCsd$Ndiff < 3),]\n", "table(data$Reward)\n", "\n", "# remove leves of reward as due to the ramp up they were not equally distributed across participants\n", "rews=c(0.05,0.1)\n", "data2 <- data[ ! data$Reward %in% rews, ]" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "boundary (singular) fit: see ?isSingular\n" ] }, { "data": { "text/plain": [ "Generalized linear mixed model fit by maximum likelihood (Laplace\n", " Approximation) [glmerMod]\n", " Family: binomial ( logit )\n", "Formula: Cheated ~ 1 + Ndiff + Reward + Trial_Nr + RT + (1 + Ndiff + Reward + \n", " RT + Trial_Nr | sub)\n", " Data: data2\n", "Control: glmerControl(optimizer = \"bobyqa\")\n", "\n", " AIC BIC logLik deviance df.resid \n", " 2094.9 2210.3 -1027.5 2054.9 2344 \n", "\n", "Scaled residuals: \n", " Min 1Q Median 3Q Max \n", "-6.3498 -0.4750 -0.1828 0.4144 5.8254 \n", "\n", "Random effects:\n", " Groups Name Variance Std.Dev. Corr \n", " sub (Intercept) 4.98823 2.2334 \n", " Ndiff 0.05959 0.2441 0.68 \n", " Reward 0.20635 0.4543 0.73 0.61 \n", " RT 0.04729 0.2175 -0.02 -0.65 0.13 \n", " Trial_Nr 0.16507 0.4063 0.73 0.69 0.51 -0.46\n", "Number of obs: 2364, groups: sub, 33\n", "\n", "Fixed effects:\n", " Estimate Std. Error z value Pr(>|z|) \n", "(Intercept) -0.58216 0.39899 -1.459 0.1445 \n", "Ndiff 1.02495 0.07968 12.864 <2e-16 ***\n", "Reward -0.09512 0.10187 -0.934 0.3505 \n", "Trial_Nr 0.01076 0.09399 0.114 0.9089 \n", "RT -0.15688 0.08987 -1.746 0.0809 . \n", "---\n", "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n", "\n", "Correlation of Fixed Effects:\n", " (Intr) Ndiff Reward Trl_Nr\n", "Ndiff 0.337 \n", "Reward 0.585 0.246 \n", "Trial_Nr 0.560 0.272 0.309 \n", "RT 0.017 -0.222 0.063 -0.103\n", "convergence code: 0\n", "boundary (singular) fit: see ?isSingular\n" ] }, "metadata": {}, "output_type": "display_data" }, { "ename": "ERROR", "evalue": "Error in plot_raw(m.run): could not find function \"plot_raw\"\n", "output_type": "error", "traceback": [ "Error in plot_raw(m.run): could not find function \"plot_raw\"\nTraceback:\n" ] } ], "source": [ "# multilevel model\n", "m.run = glmer(Cheated ~ 1 + Ndiff + Reward + Trial_Nr + RT + (1 + Ndiff + Reward + RT + Trial_Nr |sub),\n", " family = 'binomial',\n", " control = glmerControl(optimizer = 'bobyqa'),\n", " data2)\n", "\n", "summary(m.run)\n", "plot_raw(m.run)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Stroop Behavior" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "text/html": [ "32" ], "text/latex": [ "32" ], "text/markdown": [ "32" ], "text/plain": [ "[1] 32" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# load subs\n", "Stroop=read.csv('/data/sebastian/EEG/Behavioral/Stroop-all_repo.csv', header = TRUE, sep = \",\")\n", "to_rem<-c('S23','S13' ) # remove subs with bad data\n", "Stroop2 <- Stroop[ ! Stroop$sub %in% to_rem, ]\n", "length(unique(Stroop2$sub))" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Linear mixed model fit by REML ['lmerMod']\n", "Formula: RT ~ 1 + Cong + Corresp + Cong * Corresp + (1 + Cong + Corresp | \n", " sub)\n", " Data: Stroop2\n", "\n", "REML criterion at convergence: 34029\n", "\n", "Scaled residuals: \n", " Min 1Q Median 3Q Max \n", "-4.1723 -0.5598 -0.1469 0.3386 5.4875 \n", "\n", "Random effects:\n", " Groups Name Variance Std.Dev. Corr \n", " sub (Intercept) 31529 177.56 \n", " Cong2 7649 87.46 0.44 \n", " Corresp2 4399 66.32 -0.12 0.52\n", " Residual 92631 304.35 \n", "Number of obs: 2376, groups: sub, 32\n", "\n", "Fixed effects:\n", " Estimate Std. Error t value\n", "(Intercept) 700.38 33.83 20.70\n", "Cong2 282.37 23.55 11.99\n", "Corresp2 306.20 21.27 14.39\n", "Cong2:Corresp2 -354.98 25.09 -14.15\n", "\n", "Correlation of Fixed Effects:\n", " (Intr) Cong2 Crrsp2\n", "Cong2 0.070 \n", "Corresp2 -0.280 0.506 \n", "Cng2:Crrsp2 0.186 -0.533 -0.589" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "\n", "\n", "\n", "\t\n", "\t\n", "\t\n", "\t\n", "\n", "
numDFdenDFF-valuep-value
(Intercept)1 2341 613.828390
Cong1 2341 74.565880
Corresp1 2341 107.030770
Cong:Corresp1 2341 193.099530
\n" ], "text/latex": [ "\\begin{tabular}{r|llll}\n", " & numDF & denDF & F-value & p-value\\\\\n", "\\hline\n", "\t(Intercept) & 1 & 2341 & 613.82839 & 0 \\\\\n", "\tCong & 1 & 2341 & 74.56588 & 0 \\\\\n", "\tCorresp & 1 & 2341 & 107.03077 & 0 \\\\\n", "\tCong:Corresp & 1 & 2341 & 193.09953 & 0 \\\\\n", "\\end{tabular}\n" ], "text/markdown": [ "\n", "| | numDF | denDF | F-value | p-value | \n", "|---|---|---|---|\n", "| (Intercept) | 1 | 2341 | 613.82839 | 0 | \n", "| Cong | 1 | 2341 | 74.56588 | 0 | \n", "| Corresp | 1 | 2341 | 107.03077 | 0 | \n", "| Cong:Corresp | 1 | 2341 | 193.09953 | 0 | \n", "\n", "\n" ], "text/plain": [ " numDF denDF F-value p-value\n", "(Intercept) 1 2341 613.82839 0 \n", "Cong 1 2341 74.56588 0 \n", "Corresp 1 2341 107.03077 0 \n", "Cong:Corresp 1 2341 193.09953 0 " ] }, "metadata": {}, "output_type": "display_data" }, { "data": {}, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAIAAAByhViMAAAACXBIWXMAABJ0AAASdAHeZh94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\nAAAASUVORK5CYII=", "text/plain": [ "plot without title" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# multilevel model\n", "Stroop2$Corresp<-as.factor(Stroop2$Corresp)\n", "Stroop2$Cong<-as.factor(Stroop2$Cong)\n", "\n", "# With random slopes\n", "m_MC_G_rintslop = lmer(\n", " RT ~ 1+ Cong + Corresp + Cong*Corresp +\n", " (1+Cong+ Corresp |sub),\n", " Stroop2)\n", "\n", "summary(m_MC_G_rintslop)\n", "\n", "# get pvalues\n", "m1 <- lme(RT~ Cong + Corresp + Cong*Corresp,random=~1|sub,data=Stroop2)\n", "anova(m1)\n", "\n", "\n", "# plot the effects\n", "library(sjPlot)\n", "\n", "plot_model(m_MC_G_rintslop, type = \"pred\", terms = c(\"Cong\", \"Corresp\"))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Predicting trial-by-trial level cheating from power in theta band" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "\n", " 0 1 \n", "1391 913 " ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "#load trial-by-trial level data for each channel\n", "base_dir='/data/sebastian/EEG/neural_analysis/Multilevel_stimlocked_CheatVsHonest'\n", "\n", "NS=read.csv(file.path(base_dir,'Trialbytrial_Power_FactorAnalysis_final.csv'), header = TRUE, sep = \",\")\n", "\n", "#remove unnecessary columns\n", "NS$X <- NULL\n", "\n", "# show proportion of honest vs cheat\n", "table(NS$Cheat)\n", "\n", "# load cheatcount\n", "CC_all=read.csv('/data/sebastian/EEG/Behavioral/CC_all_repo.csv')\n", "colnames(CC_all)[3]<-'CC'\n", "\n", "# merge Cheatcount and TbT data\n", "mC<-merge(NS,CC_all,by=\"sub\", sort = F)\n", "#head(mC)\n", "\n", "# remove unneeded column\n", "mC$X<-NULL\n", "\n", "# remove Cheat\n", "subset<-subset(mC, select=-c(Cheat,sub))\n", "\n", "# scale the data\n", "mCsd<-as.data.frame(scale(subset))\n", "mCsd$Cheated<-mC$Cheat\n", "mCsd$sub<-as.factor(mC$sub)\n", "#head(mCsd)\n", "\n", "length(unique(mCsd$sub))" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 1\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 2\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 3\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 4\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 5\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 6\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 7\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 8\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 9\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 10\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 11\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 12\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 13\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 14\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 15\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 16\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 17\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 18\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 19\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 20\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 21\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 22\"\n", "[1] \"FC2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 23\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 24\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 25\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 26\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 27\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 28\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 29\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 30\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 31\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 32\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 33\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 34\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 35\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 36\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 37\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 38\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 39\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 40\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 41\"\n", "[1] \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 42\"\n", "[1] \"FCz_1\" \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 43\"\n", "[1] \"FCz_1\" \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 44\"\n", "[1] \"FCz_1\" \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 45\"\n", "[1] \"FCz_1\" \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 46\"\n", "[1] \"FCz_1\" \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 47\"\n", "[1] \"FCz_1\" \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 48\"\n", "[1] \"FCz_1\" \"FC2_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 49\"\n", "[1] \"FCz_1\" \"FC2_1\" \"FC1_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 50\"\n", "[1] \"FCz_1\" \"FC2_1\" \"FC1_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 51\"\n", "[1] \"FCz_1\" \"FC2_1\" \"FC1_1\" \"F2_1\" \"F1_1\" \"Fz_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "data": { "text/plain": [ "Call:\n", "glmmLasso(fix = Cheated ~ 1 + FCz_1 + FC2_1 + FC1_1 + F2_1 + \n", " F1_1 + +Fz_1 + Cz_1 + C1_1 + C2_2 + CC + FCz_1:CC + FC2_1:CC + \n", " FC1_1:CC + F2_1:CC + F1_1:CC + +Fz_1:CC + Cz_1:CC + C1_1:CC + \n", " C2_1:CC, rnd = list(sub = ~1), data = mCsd, lambda = lambda[opt3], \n", " family = family, switch.NR = F, final.re = TRUE, control = list(start = Delta.start[opt3, \n", " ], q_start = Q.start[opt3]))\n", "\n", "\n", "Fixed Effects:\n", "\n", "Coefficients:\n", " Estimate StdErr z.value p.value \n", "(Intercept) -0.545863 0.058685 -9.3015 < 2.2e-16 ***\n", "FCz_1 0.000000 NA NA NA \n", "FC2_1 -0.085034 0.053811 -1.5802 0.114056 \n", "FC1_1 0.000000 NA NA NA \n", "F2_1 0.000000 NA NA NA \n", "F1_1 0.104308 0.053803 1.9387 0.052537 . \n", "Fz_1 0.000000 NA NA NA \n", "Cz_1 0.000000 NA NA NA \n", "C1_1 0.000000 NA NA NA \n", "C2_2 0.000000 NA NA NA \n", "CC 1.616594 0.070186 23.0330 < 2.2e-16 ***\n", "FCz_1:CC 0.000000 NA NA NA \n", "FC2_1:CC 0.000000 NA NA NA \n", "FC1_1:CC 0.000000 NA NA NA \n", "F2_1:CC 0.000000 NA NA NA \n", "F1_1:CC 0.000000 NA NA NA \n", "Fz_1:CC -0.168748 0.063573 -2.6544 0.007945 ** \n", "Cz_1:CC 0.000000 NA NA NA \n", "C1_1:CC 0.000000 NA NA NA \n", "CC:C2_1 0.000000 NA NA NA \n", "---\n", "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n", "\n", "Random Effects:\n", "\n", "StdDev:\n", " sub\n", "sub 0.1237357" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "[1] 24\n" ] } ], "source": [ "\n", "\n", "################## More Elegant Method ############################################\n", "## Idea: start with big lambda and use the estimates of the previous fit (BUT: before\n", "## the final re-estimation Fisher scoring is performed!) as starting values for the next fit;\n", "## make sure, that your lambda sequence starts at a value big enough such that all covariates are\n", "## shrinked to zero;\n", "\n", "mCsd$sub<-as.factor(mCsd$sub)\n", "\n", "\n", "## Using BIC (or AIC, respectively) to determine the optimal tuning parameter lambda\n", "\n", "lambda <- seq(25,0,by=-0.5)\n", "\n", "\n", "BIC_vec<-rep(Inf,length(lambda))\n", "#family = poisson(link = log)\n", "family = binomial(link=logit)\n", "# specify starting values for the very first fit; pay attention that Delta.start has suitable length! \n", "Delta.start<-as.matrix(t(rep(0,60)))\n", "Q.start<-0.1 \n", "\n", "for(j in 1:length(lambda))\n", "{\n", " print(paste(\"Iteration \", j,sep=\"\"))\n", " \n", " glm3 <- glmmLasso(Cheated~ 1 +FCz_1 + FC2_1 + FC1_1 + F2_1 + F1_1 + \n", " + Fz_1 + Cz_1 + C1_1 + C2_2 + CC\n", " +FCz_1:CC + FC2_1:CC + FC1_1:CC + F2_1:CC + F1_1:CC + \n", " + Fz_1:CC + Cz_1:CC + C1_1:CC + C2_1:CC\n", " ,rnd = list(sub=~1), \n", " family = family, data = mCsd, \n", " lambda=lambda[j], switch.NR=F,final.re=TRUE,\n", " control = list(start=Delta.start[j,],q_start=Q.start[j])) \n", " \n", " print(colnames(glm3$Deltamatrix)[2:7][glm3$Deltamatrix[glm3$conv.step,2:7]!=0])\n", " BIC_vec[j]<-glm3$bic\n", " Delta.start<-rbind(Delta.start,glm3$Deltamatrix[glm3$conv.step,])\n", " Q.start<-c(Q.start,glm3$Q_long[[glm3$conv.step+1]])\n", "}\n", "\n", "opt3<-which.min(BIC_vec)\n", "\n", "glm3_final <- glmmLasso(Cheated~1 +FCz_1 + FC2_1 + FC1_1 + F2_1 + F1_1 + \n", " + Fz_1 + Cz_1 + C1_1 + C2_2 + CC\n", " +FCz_1:CC + FC2_1:CC + FC1_1:CC + F2_1:CC + F1_1:CC + \n", " + Fz_1:CC + Cz_1:CC + C1_1:CC + C2_1:CC,\n", " rnd = list(sub=~1), \n", " family = family, data = mCsd, lambda=lambda[opt3],\n", " switch.NR=F,final.re=TRUE,\n", " control = list(start=Delta.start[opt3,],q_start=Q.start[opt3])) \n", "\n", "\n", "summary(glm3_final)\n", "\n", "print(lambda[opt3])" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "boundary (singular) fit: see ?isSingular\n" ] }, { "data": { "text/plain": [ "Generalized linear mixed model fit by maximum likelihood (Laplace\n", " Approximation) [glmerMod]\n", " Family: binomial ( logit )\n", "Formula: Cheated ~ CC + FC2_1 + F1_1 + Fz_1:CC + (1 | sub)\n", " Data: mCsd\n", "Control: glmerControl(optimizer = \"bobyqa\")\n", "\n", " AIC BIC logLik deviance df.resid \n", " 2171.5 2206.0 -1079.8 2159.5 2298 \n", "\n", "Scaled residuals: \n", " Min 1Q Median 3Q Max \n", "-3.9242 -0.4993 -0.2942 0.5107 3.7305 \n", "\n", "Random effects:\n", " Groups Name Variance Std.Dev.\n", " sub (Intercept) 0 0 \n", "Number of obs: 2304, groups: sub, 33\n", "\n", "Fixed effects:\n", " Estimate Std. Error z value Pr(>|z|) \n", "(Intercept) -0.54189 0.05399 -10.038 < 2e-16 ***\n", "CC 1.60030 0.06558 24.404 < 2e-16 ***\n", "FC2_1 -0.08512 0.05384 -1.581 0.11391 \n", "F1_1 0.10398 0.05383 1.932 0.05341 . \n", "CC:Fz_1 -0.16603 0.06308 -2.632 0.00849 ** \n", "---\n", "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n", "\n", "Correlation of Fixed Effects:\n", " (Intr) CC FC2_1 F1_1 \n", "CC -0.111 \n", "FC2_1 -0.006 -0.045 \n", "F1_1 -0.030 0.060 -0.123 \n", "CC:Fz_1 -0.007 -0.142 0.042 -0.048\n", "convergence code: 0\n", "boundary (singular) fit: see ?isSingular\n" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# using simple multilevel model for plotting\n", "\n", "means_model = glmer(\n", "Cheated~ CC+ FC2_1 + F1_1 + Fz_1:CC\n", " + (1 |sub),\n", " family = 'binomial',\n", " control = glmerControl(optimizer = 'bobyqa'),\n", " mCsd)\n", "\n", "summary(means_model)" ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "data": {}, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAIAAAByhViMAAAACXBIWXMAABJ0AAASdAHeZh94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", "text/plain": [ "plot without title" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# plot\n", "ef1 <- effect(term=\"CC:Fz_1\", xlevels= list(CC=c(-3,-2,-1,1, 2, 3)), mod=means_model)\n", "efdata1<-as.data.frame(ef1) #convert the effects list to a data frame\n", "#efdata1 #print effects data frame\n", "efdata1$PersMeanCent_DailyControl<-as.factor(efdata1$CC)\n", "\n", "\n", "# plot the interaction\n", "\n", "ggplot(efdata1, aes(x=Fz_1, y=fit, color=CC,group=CC)) + \n", " geom_point() + \n", " geom_line(size=1.2) + \n", " #xlim(-5, 4) +\n", " \n", " #scale_color_brewer(palette = \"Dark2\") +\n", " geom_ribbon(aes(ymin=fit-se, ymax=fit+se, fill=CC),alpha=0.3) + \n", " #scale_colour_gradientn(colours=rainbow(4)) +\n", " labs(title = \"Interaction: CheatCount * Fz\", x= \"Power at Fz\", y=\"Probability of cheating\", color=\"CheatCount\", fill=\"CheatCount\") + theme_minimal() + theme(text=element_text(size=20))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Robustness check using theta power mean over all 9 channels" ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "boundary (singular) fit: see ?isSingular\n" ] }, { "data": { "text/plain": [ "Generalized linear mixed model fit by maximum likelihood (Laplace\n", " Approximation) [glmerMod]\n", " Family: binomial ( logit )\n", "Formula: Cheated ~ CC + ChannelsMeans + ChannelsMeans:CC + (1 | sub)\n", " Data: mCsd\n", "Control: glmerControl(optimizer = \"bobyqa\")\n", "\n", " AIC BIC logLik deviance df.resid \n", " 2175.8 2204.5 -1082.9 2165.8 2299 \n", "\n", "Scaled residuals: \n", " Min 1Q Median 3Q Max \n", "-3.9946 -0.4986 -0.2926 0.5041 3.7463 \n", "\n", "Random effects:\n", " Groups Name Variance Std.Dev.\n", " sub (Intercept) 0 0 \n", "Number of obs: 2304, groups: sub, 33\n", "\n", "Fixed effects:\n", " Estimate Std. Error z value Pr(>|z|) \n", "(Intercept) -0.54038 0.05395 -10.016 <2e-16 ***\n", "CC 1.59224 0.06518 24.427 <2e-16 ***\n", "ChannelsMeans -0.05931 0.11521 -0.515 0.6067 \n", "CC:ChannelsMeans -0.31079 0.13524 -2.298 0.0216 * \n", "---\n", "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n", "\n", "Correlation of Fixed Effects:\n", " (Intr) CC ChnnlM\n", "CC -0.109 \n", "ChannelsMns -0.055 -0.008 \n", "CC:ChnnlsMn -0.001 -0.114 0.000\n", "convergence code: 0\n", "boundary (singular) fit: see ?isSingular\n" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "\n", "# compute channel means\n", "Stroop_chs<-mCsd %>% select( FCz_1, FC1_1, FC2_1, F1_1, F2_1, Fz_1, C1_1, Cz_1, C2_1)\n", "mCsd$ChannelsMeans=rowMeans(Stroop_chs)\n", "\n", "# Multilevel model using channel means\n", "means_model = glmer(\n", "Cheated~ CC+ ChannelsMeans + ChannelsMeans:CC \n", " + (1 |sub),\n", " family = 'binomial',\n", " control = glmerControl(optimizer = 'bobyqa'),\n", " mCsd)\n", "\n", "summary(means_model)" ] }, { "cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [ { "data": {}, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAIAAAByhViMAAAACXBIWXMAABJ0AAASdAHeZh94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\nQmCC", "text/plain": [ "plot without title" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "ef1 <- effect(term=\"CC:ChannelsMeans\", xlevels= list(CC=c(-3,-2,-1,1, 2, 3)), mod=means_model)\n", "efdata1<-as.data.frame(ef1) #convert the effects list to a data frame\n", "#efdata1 #print effects data frame\n", "efdata1$PersMeanCent_DailyControl<-as.factor(efdata1$CC)\n", "\n", "\n", "# plot the interaction\n", "\n", "ggplot(efdata1, aes(x=ChannelsMeans, y=fit, color=CC,group=CC)) + \n", " geom_point() + \n", " geom_line(size=1.2) + \n", " #xlim(-5, 4) +\n", " \n", " #scale_color_brewer(palette = \"Dark2\") +\n", " geom_ribbon(aes(ymin=fit-se, ymax=fit+se, fill=CC),alpha=0.3) + \n", " #scale_colour_gradientn(colours=rainbow(4)) +\n", " labs(title = \"Interaction: CheatCount*mean channels\", x= \"Power in mean channels\", y=\"Probability of cheating\", color=\"CheatCount\", fill=\"CheatCount\") + theme_minimal() + theme(text=element_text(size=20))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Multilevel Analysis for Similarity Data" ] }, { "cell_type": "code", "execution_count": 37, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "\n", " 0 1 \n", "1328 908 " ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "32" ], "text/latex": [ "32" ], "text/markdown": [ "32" ], "text/plain": [ "[1] 32" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "#load similarity data\n", "base_dir='/data/sebastian/EEG/neural_analysis/Multilevel_stimlocked_CheatVsHonest_similarityBased_forRev'\n", "\n", "NS=read.csv(file.path(base_dir,'Trialbytrial_Power_selChannels_thetaRange_SimilarityBasedForRev_subspec_moreChannels_theta_diff_z.csv'), header = TRUE, sep = \",\")\n", "\n", "#remove unnecessary columns\n", "NS$X <- NULL\n", "\n", "# show proportion of honest vs cheat\n", "table(NS$Cheat)\n", "\n", "\n", "CC_all=read.csv('/data/sebastian/EEG/Behavioral/CC_all_repo.csv')\n", "colnames(CC_all)[3]<-'CC'\n", "\n", "# merge Cheatcount and TbT data\n", "mC<-merge(NS,CC_all,by=\"sub\", sort = F)\n", "\n", "# remove unneeded column\n", "mC$X<-NULL\n", "\n", "# remove Cheat\n", "subset<-subset(mC, select=-c(Cheat,sub))\n", "\n", "# scale the data\n", "mCsd<-as.data.frame(scale(subset))\n", "mCsd$Cheated<-mC$Cheat\n", "mCsd$sub<-as.factor(mC$sub)\n", "\n", "length(unique(mCsd$sub))" ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 1\"\n", "[1] \"FC1_1\" \"FCz_1\" \"FC2_1\" \"F2_1\" \"Fz_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 2\"\n", "[1] \"FC1_1\" \"FCz_1\" \"FC2_1\" \"F2_1\" \"Fz_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 3\"\n", "[1] \"FC1_1\" \"FC2_1\" \"F2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 4\"\n", "[1] \"FC1_1\" \"F2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 5\"\n", "[1] \"FC1_1\" \"F2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 6\"\n", "[1] \"FC1_1\" \"F2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 7\"\n", "[1] \"FC1_1\" \"F2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 8\"\n", "[1] \"FC1_1\" \"F2_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 9\"\n", "[1] \"FC1_1\" \"FCz_1\" \"FC2_1\" \"F2_1\" \"Fz_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 10\"\n", "[1] \"FC1_1\" \"FCz_1\" \"FC2_1\" \"F2_1\" \"Fz_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 11\"\n", "[1] \"FC1_1\" \"FCz_1\" \"FC2_1\" \"F2_1\" \"Fz_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 12\"\n", "[1] \"FC1_1\" \"FCz_1\" \"FC2_1\" \"F2_1\" \"Fz_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 13\"\n", "[1] \"FC1_1\" \"FCz_1\" \"FC2_1\" \"F2_1\" \"Fz_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 14\"\n", "[1] \"FC1_1\" \"FCz_1\" \"FC2_1\" \"F2_1\" \"Fz_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 15\"\n", "[1] \"FC1_1\" \"FCz_1\" \"FC2_1\" \"F2_1\" \"Fz_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 16\"\n", "[1] \"FC1_1\" \"FCz_1\" \"FC2_1\" \"F2_1\" \"Fz_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 17\"\n", "[1] \"FC1_1\" \"FCz_1\" \"FC2_1\" \"F2_1\" \"Fz_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 18\"\n", "[1] \"FC1_1\" \"FCz_1\" \"FC2_1\" \"F2_1\" \"Fz_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 19\"\n", "[1] \"FC1_1\" \"FCz_1\" \"FC2_1\" \"F2_1\" \"Fz_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 20\"\n", "[1] \"FC1_1\" \"FCz_1\" \"FC2_1\" \"F2_1\" \"Fz_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[1] \"Iteration 21\"\n", "[1] \"FC1_1\" \"FCz_1\" \"FC2_1\" \"F2_1\" \"Fz_1\" \"F1_1\" \n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Warning message in rbind(Delta.start, glm3$Deltamatrix[glm3$conv.step, ]):\n", "“number of columns of result is not a multiple of vector length (arg 2)”" ] }, { "data": { "text/plain": [ "Call:\n", "glmmLasso(fix = Cheated ~ FC1_1 + FCz_1 + FC2_1 + F2_1 + Fz_1 + \n", " F1_1 + C1_1 + C2_1 + Cz_1 + CC + FCz_1:CC + FC2_1:CC + FC1_1:CC + \n", " F2_1:CC + F1_1:CC + Fz_1:CC + C1_1:CC + C2_1:CC + Cz_1:CC, \n", " rnd = list(sub = ~1), data = mCsd, lambda = lambda[opt3], \n", " family = family, switch.NR = F, final.re = TRUE, control = list(start = Delta.start[opt3, \n", " ], q_start = Q.start[opt3]))\n", "\n", "\n", "Fixed Effects:\n", "\n", "Coefficients:\n", " Estimate StdErr z.value p.value \n", "(Intercept) -0.4797865 0.0579150 -8.2843 < 2e-16 ***\n", "FC1_1 -0.0282987 0.0586278 -0.4827 0.62932 \n", "FCz_1 0.0000000 NA NA NA \n", "FC2_1 0.0000000 NA NA NA \n", "F2_1 0.0667666 0.0566498 1.1786 0.23856 \n", "Fz_1 0.0000000 NA NA NA \n", "F1_1 -0.0086197 0.0572664 -0.1505 0.88036 \n", "C1_1 0.0000000 NA NA NA \n", "C2_1 0.0378518 0.0591148 0.6403 0.52197 \n", "Cz_1 -0.0633748 0.0580669 -1.0914 0.27509 \n", "CC 1.6197017 0.0714423 22.6715 < 2e-16 ***\n", "FCz_1:CC 0.1105244 0.0766462 1.4420 0.14930 \n", "FC2_1:CC 0.0620888 0.0696370 0.8916 0.37260 \n", "FC1_1:CC -0.1578927 0.0682846 -2.3123 0.02076 * \n", "F2_1:CC -0.0843246 0.0831240 -1.0144 0.31037 \n", "F1_1:CC 0.0795226 0.0751099 1.0588 0.28971 \n", "Fz_1:CC 0.1259226 0.0733531 1.7167 0.08604 . \n", "C1_1:CC -0.0978061 0.0826165 -1.1839 0.23647 \n", "C2_1:CC -0.0542497 0.0749038 -0.7243 0.46891 \n", "Cz_1:CC 0.0000000 NA NA NA \n", "---\n", "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n", "\n", "Random Effects:\n", "\n", "StdDev:\n", " sub\n", "sub 0.09871306" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "[1] 2.6\n" ] } ], "source": [ "\n", "\n", "################## More Elegant Method ############################################\n", "## Idea: start with big lambda and use the estimates of the previous fit (BUT: before\n", "## the final re-estimation Fisher scoring is performed!) as starting values for the next fit;\n", "## make sure, that your lambda sequence starts at a value big enough such that all covariates are\n", "## shrinked to zero;\n", "\n", "mCsd$sub<-as.factor(mCsd$sub)\n", "\n", "\n", "## Using BIC (or AIC, respectively) to determine the optimal tuning parameter lambda\n", "\n", "lambda <- seq(4,0,by=-0.2) # 15 0.06 for subspec theta\n", "\n", "BIC_vec<-rep(Inf,length(lambda))\n", "#family = poisson(link = log)\n", "family = binomial(link=logit)\n", "# specify starting values for the very first fit; pay attention that Delta.start has suitable length! \n", "Delta.start<-as.matrix(t(rep(0,60)))\n", "Q.start<-0.1 \n", "\n", "for(j in 1:length(lambda))\n", "{\n", " print(paste(\"Iteration \", j,sep=\"\"))\n", " \n", " glm3 <- glmmLasso(Cheated~ 1 +FC1_1+FCz_1 + FC2_1 + F2_1\n", " + Fz_1 + F1_1 + C1_1 + C2_1+ Cz_1 + CC\n", " +FCz_1:CC + FC2_1:CC + FC1_1:CC + F2_1:CC\n", " + F1_1:CC + Fz_1:CC + C1_1:CC + C2_1:CC + Cz_1:CC \n", " ,rnd = list(sub=~1), \n", " family = family, data = mCsd, \n", " lambda=lambda[j], switch.NR=F,final.re=TRUE,\n", " control = list(start=Delta.start[j,],q_start=Q.start[j])) \n", " \n", " print(colnames(glm3$Deltamatrix)[2:7][glm3$Deltamatrix[glm3$conv.step,2:7]!=0])\n", " BIC_vec[j]<-glm3$bic\n", " Delta.start<-rbind(Delta.start,glm3$Deltamatrix[glm3$conv.step,])\n", " Q.start<-c(Q.start,glm3$Q_long[[glm3$conv.step+1]])\n", "}\n", "\n", "opt3<-which.min(BIC_vec)\n", "\n", "glm3_final <- glmmLasso(Cheated~FC1_1+FCz_1 + FC2_1 + F2_1\n", " + Fz_1 + F1_1 + C1_1 + C2_1+ Cz_1 + CC\n", " +FCz_1:CC + FC2_1:CC + FC1_1:CC + F2_1:CC\n", " + F1_1:CC + Fz_1:CC + C1_1:CC + C2_1:CC + Cz_1:CC ,\n", " rnd = list(sub=~1), \n", " family = family, data = mCsd, lambda=lambda[opt3],\n", " switch.NR=F,final.re=TRUE,\n", " control = list(start=Delta.start[opt3,],q_start=Q.start[opt3])) \n", "\n", "\n", "summary(glm3_final)\n", "\n", "print(lambda[opt3])" ] }, { "cell_type": "code", "execution_count": 39, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "boundary (singular) fit: see ?isSingular\n", "\n", "Correlation matrix not shown by default, as p = 20 > 12.\n", "Use print(obj, correlation=TRUE) or\n", " vcov(obj) if you need it\n", "\n" ] }, { "data": { "text/plain": [ "Generalized linear mixed model fit by maximum likelihood (Laplace\n", " Approximation) [glmerMod]\n", " Family: binomial ( logit )\n", "Formula: Cheated ~ CC + FC1_1 + FCz_1 + FC2_1 + F2_1 + Fz_1 + F1_1 + C1_1 + \n", " C2_1 + Cz_1 + CC + FCz_1:CC + FC2_1:CC + FC1_1:CC + F2_1:CC + \n", " F1_1:CC + Fz_1:CC + C1_1:CC + C2_1:CC + Cz_1:CC + (1 | sub)\n", " Data: mCsd\n", "Control: glmerControl(optimizer = \"bobyqa\")\n", "\n", " AIC BIC logLik deviance df.resid \n", " 2158.5 2278.4 -1058.2 2116.5 2215 \n", "\n", "Scaled residuals: \n", " Min 1Q Median 3Q Max \n", "-4.5554 -0.5302 -0.2819 0.5322 4.5449 \n", "\n", "Random effects:\n", " Groups Name Variance Std.Dev.\n", " sub (Intercept) 0 0 \n", "Number of obs: 2236, groups: sub, 32\n", "\n", "Fixed effects:\n", " Estimate Std. Error z value Pr(>|z|) \n", "(Intercept) -0.477609 0.054951 -8.691 <2e-16 ***\n", "CC 1.610232 0.068571 23.483 <2e-16 ***\n", "FC1_1 -0.034237 0.061712 -0.555 0.5790 \n", "FCz_1 0.014277 0.064498 0.221 0.8248 \n", "FC2_1 0.007941 0.057586 0.138 0.8903 \n", "F2_1 0.067677 0.065834 1.028 0.3039 \n", "Fz_1 -0.013061 0.061102 -0.214 0.8307 \n", "F1_1 -0.004572 0.060467 -0.076 0.9397 \n", "C1_1 -0.001940 0.071063 -0.027 0.9782 \n", "C2_1 0.038790 0.059335 0.654 0.5133 \n", "Cz_1 -0.066398 0.060623 -1.095 0.2734 \n", "CC:FCz_1 0.106606 0.076734 1.389 0.1647 \n", "CC:FC2_1 0.061675 0.069369 0.889 0.3740 \n", "CC:FC1_1 -0.155154 0.067988 -2.282 0.0225 * \n", "CC:F2_1 -0.084013 0.083333 -1.008 0.3134 \n", "CC:F1_1 0.076312 0.075443 1.012 0.3118 \n", "CC:Fz_1 0.128851 0.074229 1.736 0.0826 . \n", "CC:C1_1 -0.097905 0.086064 -1.138 0.2553 \n", "CC:C2_1 -0.056670 0.075943 -0.746 0.4555 \n", "CC:Cz_1 -0.004690 0.074632 -0.063 0.9499 \n", "---\n", "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n", "convergence code: 0\n", "boundary (singular) fit: see ?isSingular\n" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# multilevel model for plotting\n", "multi_model = glmer(\n", "Cheated~ CC+FC1_1+FCz_1 + FC2_1 + F2_1\n", " + Fz_1 + F1_1 + C1_1 + C2_1+ Cz_1 + CC\n", " +FCz_1:CC + FC2_1:CC + FC1_1:CC + F2_1:CC\n", " + F1_1:CC + Fz_1:CC + C1_1:CC + C2_1:CC + Cz_1:CC \n", " + (1 |sub),\n", " family = 'binomial',\n", " control = glmerControl(optimizer = 'bobyqa'),\n", " mCsd)\n", "\n", "summary(multi_model)\n" ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [ { "data": {}, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAIAAAByhViMAAAACXBIWXMAABJ0AAASdAHeZh94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", "text/plain": [ "plot without title" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "ef1 <- effect(term=\"CC:FC1_1\", xlevels= list(CC=c(-3,-2,-1,1, 2, 3)), mod=multi_model)\n", "efdata1<-as.data.frame(ef1) #convert the effects list to a data frame\n", "#efdata1 #print effects data frame\n", "efdata1$PersMeanCent_DailyControl<-as.factor(efdata1$CC)\n", "\n", "\n", "# plot the interaction\n", "\n", "ggplot(efdata1, aes(x=FC1_1, y=fit, color=CC,group=CC)) + \n", " geom_point() + \n", " geom_line(size=1.2) + \n", " #xlim(-5, 4) +\n", " \n", " #scale_color_brewer(palette = \"Dark2\") +\n", " geom_ribbon(aes(ymin=fit-se, ymax=fit+se, fill=CC),alpha=0.3) + \n", " #scale_colour_gradientn(colours=rainbow(4)) +\n", " labs(title = \"Interaction: CheatCount * Similarity\", x= \"Similiarity to Stroop Cognitive Control\", y=\"Probability of cheating\", color=\"CheatCount\", fill=\"CheatCount\") + theme_minimal() + theme(text=element_text(size=20))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Multicollinearity" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "## aggregate across subs\n", "\n", "agg_mCsd = aggregate(mCsd,\n", " by = list(mCsd$sub),\n", " FUN = mean)\n", "\n", "# compute correlations\n", "Stroop_chs_agg<-agg_mCsd %>% select(FC1_1, FCz_1, FC2_1, F1_1, Fz_1, F2_1, C1_1, Cz_1, C2_1)\n", "\n", "\n", "\n", "\n", "r_agg<-rcorr(as.matrix(Stroop_chs_agg))\n", "\n", "#plot\n", "library(corrplot)\n", "corrplot(r_agg$r, type = \"upper\", addCoef.col = \"black\",\n", " p.mat = r_agg$P,\n", " tl.col = \"black\", sig.level=0.05, insig = \"blank\", tl.srt = 45)\n" ] } ], "metadata": { "kernelspec": { "display_name": "R", "language": "R", "name": "ir" }, "language_info": { "codemirror_mode": "r", "file_extension": ".r", "mimetype": "text/x-r-source", "name": "R", "pygments_lexer": "r", "version": "3.6.3" } }, "nbformat": 4, "nbformat_minor": 4 }