# Load necessary libraries
library(readr)
library(tidyverse, quietly = TRUE)
library(readxl)
library(stringr)
library(mice)
library(lme4)
library(lmerTest)
library(performance)
#Function to remove outliers based on IQR
remove_outliers <- function(df, column) {
Q1 <- quantile(df[[column]], 0.25, na.rm = TRUE)
Q3 <- quantile(df[[column]], 0.75, na.rm = TRUE)
IQR <- Q3 - Q1
lower_bound <- Q1 - 1.5 * IQR
upper_bound <- Q3 + 1.5 * IQR
df <- dplyr::filter(df, df[[column]] >= lower_bound & df[[column]] <= upper_bound)
return(df)
}
# Load data
MergeFlankerDec8 <- read_excel("C:/Users/John Majoubi/Downloads/MergeFlankerDec8.xlsx")
MergeSimonDec8th <- read_excel("C:/Users/John Majoubi/Downloads/MergeSimonDec8th.xlsx")
MergeStroopDec8Full <- read_excel("C:/Users/John Majoubi/Downloads/MergeStroopDec8Full.xlsx")
# Select relevant columns
MergeFlankerDec8_c <- MergeFlankerDec8 %>%
select(Subject, Task.RT, FinalScore, TrialType) %>%
mutate(Task.RT = as.numeric(Task.RT))
MergeFlankerDec8_c <- remove_outliers(df = MergeFlankerDec8_c, column = "Task.RT")
MergeSimonDec8th_c <- MergeSimonDec8th %>%
select(Subject, Task.RT, FinalScore, TrialType) %>%
mutate(Task.RT = as.numeric(Task.RT))
MergeSimonDec8th_c <- remove_outliers(MergeSimonDec8th_c, "Task.RT")
MergeStroopDec8Full_c <- MergeStroopDec8Full %>%
select(Subject, Task.RT, FinalScore, TrialType) %>%
mutate(Task.RT = as.numeric(Task.RT))
MergeStroopDec8Full_c <- remove_outliers(MergeStroopDec8Full_c, "Task.RT")
# Impute missing values
impute_missing_values <- function(df) {
numeric_cols <- sapply(df, is.numeric)
na_columns <- colnames(df)[numeric_cols & colSums(is.na(df)) > 0]
df[na_columns] <- lapply(df[na_columns], function(x) replace(x, is.na(x), mean(x, na.rm = TRUE)))
return(df)
}
MergeFlankerDec8_c <- impute_missing_values(MergeFlankerDec8_c)
MergeSimonDec8th_c <- impute_missing_values(MergeSimonDec8th_c)
MergeStroopDec8Full_c <- impute_missing_values(MergeStroopDec8Full_c)
# Convert Task.RT columns to numeric, handling "NULL" strings
convert_to_numeric <- function(df) {
df <- df %>%
mutate(across(starts_with("Task.RT"), ~as.numeric(str_replace(., "NULL", NA_character_))))
return(df)
}
MergeFlankerDec8_c <- convert_to_numeric(MergeFlankerDec8_c)
MergeSimonDec8th_c <- convert_to_numeric(MergeSimonDec8th_c)
MergeStroopDec8Full_c <- convert_to_numeric(MergeStroopDec8Full_c)
# Aggregate datasets by Subject
agg_Flanker <- MergeFlankerDec8_c %>%
group_by(Subject) %>%
summarise(Task.RT_Flanker = mean(Task.RT, na.rm = TRUE),
FinalScore_Flanker = mean(FinalScore, na.rm = TRUE))
agg_Simon <- MergeSimonDec8th_c %>%
group_by(Subject) %>%
summarise(Task.RT_Simon = mean(Task.RT, na.rm = TRUE),
FinalScore_Simon = mean(FinalScore, na.rm = TRUE))
agg_Stroop <- MergeStroopDec8Full_c %>%
group_by(Subject) %>%
summarise(Task.RT_Stroop = mean(Task.RT, na.rm = TRUE),
FinalScore_Stroop = mean(FinalScore, na.rm = TRUE))
# Merge aggregated datasets on 'Subject'
merged_data <- agg_Flanker %>%
full_join(agg_Simon, by = "Subject") %>%
full_join(agg_Stroop, by = "Subject")
# Check the structure of the merged data
str(merged_data)
## tibble [301 × 7] (S3: tbl_df/tbl/data.frame)
## $ Subject : num [1:301] 333 492 4037 5088 6772 ...
## $ Task.RT_Flanker : num [1:301] 1077 2223 1707 1991 2673 ...
## $ FinalScore_Flanker: num [1:301] 1 6 44 36 23 44 38 41 56 13 ...
## $ Task.RT_Simon : num [1:301] 1178 1161 1134 889 1162 ...
## $ FinalScore_Simon : num [1:301] 59 53 60 74 59 66 60 70 67 56 ...
## $ Task.RT_Stroop : num [1:301] NA 1822 1563 1306 2235 ...
## $ FinalScore_Stroop : num [1:301] NA 15 46 55 11 42 40 50 41 NA ...
# Remove rows with FinalScore below 0
MergeFlankerDec8_c <- MergeFlankerDec8_c %>% dplyr::filter(FinalScore >= 0)
MergeSimonDec8th_c <- MergeSimonDec8th_c %>% dplyr::filter(FinalScore >= 0)
MergeStroopDec8Full_c <- MergeStroopDec8Full_c %>% dplyr::filter(FinalScore >= 0)
MergeFlankerDec8_c %>% count(Subject)
## # A tibble: 262 × 2
## Subject n
## <dbl> <int>
## 1 333 66
## 2 492 35
## 3 4037 45
## 4 5088 39
## 5 6772 30
## 6 14740 47
## 7 23295 41
## 8 42195 42
## 9 43158 57
## 10 56964 25
## # ℹ 252 more rows
# remove_outliers <- function(df, column) {
# Q1 <- quantile(df[[column]], 0.25, na.rm = TRUE)
# Q3 <- quantile(df[[column]], 0.75, na.rm = TRUE)
# IQR <- Q3 - Q1
# lower_bound <- Q1 - 1.5 * IQR
# upper_bound <- Q3 + 1.5 * IQR
# df %>% filter(df[[column]] >= lower_bound & df[[column]] <= upper_bound)
# }
# MergeFlankerDec8_c %>% count(Subject)
# Model fitting and diagnostics
# Ensure Task.RT is numeric and TrialType is a factor in the original dataset
MergeFlankerDec8_c <- MergeFlankerDec8_c %>%
mutate(Task.RT = as.numeric(Task.RT),
TrialType = as.factor(TrialType))
# Fit the linear mixed-effects model
Flankermodel <- lme4::lmer(Task.RT ~ TrialType + (1 | Subject), data = MergeFlankerDec8_c)
summary(Flankermodel)
## Linear mixed model fit by REML ['lmerMod']
## Formula: Task.RT ~ TrialType + (1 | Subject)
## Data: MergeFlankerDec8_c
##
## REML criterion at convergence: 133635.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.5477 -0.5027 -0.0986 0.4445 4.6564
##
## Random effects:
## Groups Name Variance Std.Dev.
## Subject (Intercept) 307269 554.3
## Residual 670283 818.7
## Number of obs: 8182, groups: Subject, 262
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 2046.32 38.94 52.55
## TrialTypeFullyIncongruent 483.78 25.76 18.78
## TrialTypeStimCongruentRespIncongruent 350.74 25.60 13.70
## TrialTypeStimIncongruentRespCongruent 312.06 25.33 12.32
##
## Correlation of Fixed Effects:
## (Intr) TrlTFI TTSCRI
## TrlTypFllyI -0.315
## TrlTypStCRI -0.320 0.489
## TrlTypStIRC -0.325 0.493 0.496
# Count the number of subjects
MergeFlankerDec8_c %>% count(Subject)
## # A tibble: 262 × 2
## Subject n
## <dbl> <int>
## 1 333 66
## 2 492 35
## 3 4037 45
## 4 5088 39
## 5 6772 30
## 6 14740 47
## 7 23295 41
## 8 42195 42
## 9 43158 57
## 10 56964 25
## # ℹ 252 more rows
# Calculate ICC (Intraclass Correlation Coefficient)
icc(Flankermodel)
## # Intraclass Correlation Coefficient
##
## Adjusted ICC: 0.314
## Unadjusted ICC: 0.304
# Load necessary libraries
library(dplyr)
library(ggplot2)
library(patchwork)
## Warning: package 'patchwork' was built under R version 4.4.1
# Assuming merged_data is already loaded and cleaned
# Compute correlations
correlation_Flanker_Simon <- cor(merged_data$Task.RT_Flanker, merged_data$Task.RT_Simon, use = "complete.obs")
correlation_Flanker_Stroop <- cor(merged_data$Task.RT_Flanker, merged_data$Task.RT_Stroop, use = "complete.obs")
correlation_Simon_Stroop <- cor(merged_data$Task.RT_Simon, merged_data$Task.RT_Stroop, use = "complete.obs")
# Create individual plots
p1 <- ggplot(merged_data, aes(x = Task.RT_Flanker, y = Task.RT_Simon)) +
geom_point() +
geom_smooth(method = "lm") +
labs(title = "Relationship between Task.RT in Flanker and Simon",
x = "Task.RT Flanker",
y = "Task.RT Simon") +
annotate("text", x = Inf, y = Inf, label = paste("r =", round(correlation_Flanker_Simon, 2)), hjust = 1.1, vjust = 1.5, size = 5, color = "blue")
p2 <- ggplot(merged_data, aes(x = Task.RT_Flanker, y = Task.RT_Stroop)) +
geom_point() +
geom_smooth(method = "lm") +
labs(title = "Relationship between Task.RT in Flanker and Stroop",
x = "Task.RT Flanker",
y = "Task.RT Stroop") +
annotate("text", x = Inf, y = Inf, label = paste("r =", round(correlation_Flanker_Stroop, 2)), hjust = 1.1, vjust = 1.5, size = 5, color = "blue")
p3 <- ggplot(merged_data, aes(x = Task.RT_Simon, y = Task.RT_Stroop)) +
geom_point() +
geom_smooth(method = "lm") +
labs(title = "Relationship between Task.RT in Simon and Stroop",
x = "Task.RT Simon",
y = "Task.RT Stroop") +
annotate("text", x = Inf, y = Inf, label = paste("r =", round(correlation_Simon_Stroop, 2)), hjust = 1.1, vjust = 1.5, size = 5, color = "blue")
# Combine plots
combined_plot <- p1 + p2 + p3 + plot_layout(ncol = 1)
combined_plot
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 14 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 14 rows containing missing values or values outside the scale range
## (`geom_point()`).
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 17 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 17 rows containing missing values or values outside the scale range
## (`geom_point()`).
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 14 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 14 rows containing missing values or values outside the scale range
## (`geom_point()`).
# Save the combined plot
ggsave("combined_task_rt_plot.png", plot = combined_plot, dpi = 300, width = 8, height = 12, units = "in")
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 14 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Removed 14 rows containing missing values or values outside the scale range
## (`geom_point()`).
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 17 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 17 rows containing missing values or values outside the scale range
## (`geom_point()`).
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 14 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 14 rows containing missing values or values outside the scale range
## (`geom_point()`).
# Ensure Task.RT is numeric and TrialType is a factor in the original dataset
MergeFlankerDec8_c <- MergeFlankerDec8_c %>%
mutate(Task.RT = as.numeric(Task.RT),
TrialType = as.factor(TrialType))
# Fit the linear mixed-effects model
model <- lme4::lmer(Task.RT ~ TrialType + (1 | Subject), data = MergeFlankerDec8_c)
summary(model)
## Linear mixed model fit by REML ['lmerMod']
## Formula: Task.RT ~ TrialType + (1 | Subject)
## Data: MergeFlankerDec8_c
##
## REML criterion at convergence: 133635.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.5477 -0.5027 -0.0986 0.4445 4.6564
##
## Random effects:
## Groups Name Variance Std.Dev.
## Subject (Intercept) 307269 554.3
## Residual 670283 818.7
## Number of obs: 8182, groups: Subject, 262
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 2046.32 38.94 52.55
## TrialTypeFullyIncongruent 483.78 25.76 18.78
## TrialTypeStimCongruentRespIncongruent 350.74 25.60 13.70
## TrialTypeStimIncongruentRespCongruent 312.06 25.33 12.32
##
## Correlation of Fixed Effects:
## (Intr) TrlTFI TTSCRI
## TrlTypFllyI -0.315
## TrlTypStCRI -0.320 0.489
## TrlTypStIRC -0.325 0.493 0.496
# Count the number of subjects
MergeFlankerDec8_c %>% count(Subject)
## # A tibble: 262 × 2
## Subject n
## <dbl> <int>
## 1 333 66
## 2 492 35
## 3 4037 45
## 4 5088 39
## 5 6772 30
## 6 14740 47
## 7 23295 41
## 8 42195 42
## 9 43158 57
## 10 56964 25
## # ℹ 252 more rows
# Calculate ICC (Intraclass Correlation Coefficient)
icc(model)
## # Intraclass Correlation Coefficient
##
## Adjusted ICC: 0.314
## Unadjusted ICC: 0.304
# Identify influential data points using Cook's distance
influential_points <- which(cooks.distance(model) >= 1, arr.ind = TRUE)
influential_points
## named integer(0)
# Load necessary libraries
library(dplyr)
library(lme4)
# Ensure Task.RT and TrialType are of the correct types
MergeFlankerDec8_c <- MergeFlankerDec8_c %>%
mutate(Task.RT = as.numeric(Task.RT),
TrialType = as.factor(TrialType))
# Fit the traditional linear model (lm)
lm_model <- lm(Task.RT ~ TrialType, data = MergeFlankerDec8_c)
# Fit the linear mixed-effects model (lme)
lme_model <- lme4::lmer(Task.RT ~ TrialType + (1 | Subject), data = MergeFlankerDec8_c)
# Calculate BIC for both models
bic_lm <- BIC(lm_model)
bic_lme <- BIC(lme_model)
# Print the BIC values
cat("BIC for traditional linear model:", bic_lm, "\n")
## BIC for traditional linear model: 136001.9
cat("BIC for linear mixed-effects model:", bic_lme, "\n")
## BIC for linear mixed-effects model: 133689.7
# Compare the BIC values
if (bic_lm < bic_lme) {
cat("The traditional linear model has a lower BIC and is preferred.\n")
} else {
cat("The linear mixed-effects model has a lower BIC and is preferred.\n")
}
## The linear mixed-effects model has a lower BIC and is preferred.
# Compute mean FinalScore for each individual in MergeFlankerDec8_c
mean_final_score_Flanker <- MergeFlankerDec8_c %>%
group_by(Subject) %>%
summarise(mean_FinalScore_Flanker = mean(FinalScore, na.rm = TRUE))
# Compute mean Task.RT for each individual in MergeSimonDec8th_c
mean_task_rt_Simon <- MergeSimonDec8th_c %>%
group_by(Subject) %>%
summarise(mean_Task.RT_Simon = mean(Task.RT, na.rm = TRUE))
# Merge the two datasets on Subject to align them for correlation calculation
merged_data <- inner_join(mean_final_score_Flanker, mean_task_rt_Simon, by = "Subject")
# Calculate the correlation
correlation <- cor(merged_data$mean_FinalScore_Flanker, merged_data$mean_Task.RT_Simon, use = "complete.obs")
# Print the correlation
print(correlation)
## [1] -0.4714869
# Load necessary libraries
library(dplyr)
library(ggplot2)
library(patchwork)
# Compute mean FinalScore for each individual in MergeFlankerDec8_c
mean_final_score_Flanker <- MergeFlankerDec8_c %>%
group_by(Subject) %>%
summarise(mean_FinalScore_Flanker = mean(FinalScore[FinalScore >= 0], na.rm = TRUE))
# Compute mean FinalScore for each individual in MergeSimonDec8th_c
mean_final_score_Simon <- MergeSimonDec8th_c %>%
group_by(Subject) %>%
summarise(mean_FinalScore_Simon = mean(FinalScore[FinalScore >= 0], na.rm = TRUE))
# Compute mean FinalScore for each individual in MergeStroopDec8Full_c
mean_final_score_Stroop <- MergeStroopDec8Full_c %>%
group_by(Subject) %>%
summarise(mean_FinalScore_Stroop = mean(FinalScore[FinalScore >= 0], na.rm = TRUE))
# Merge the datasets on Subject to align them for correlation calculation
merged_data_final_score <- mean_final_score_Flanker %>%
full_join(mean_final_score_Simon, by = "Subject") %>%
full_join(mean_final_score_Stroop, by = "Subject")
# Calculate the correlations
correlation_Flanker_Simon_FinalScore <- cor(merged_data_final_score$mean_FinalScore_Flanker, merged_data_final_score$mean_FinalScore_Simon, use = "complete.obs")
correlation_Flanker_Stroop_FinalScore <- cor(merged_data_final_score$mean_FinalScore_Flanker, merged_data_final_score$mean_FinalScore_Stroop, use = "complete.obs")
correlation_Simon_Stroop_FinalScore <- cor(merged_data_final_score$mean_FinalScore_Simon, merged_data_final_score$mean_FinalScore_Stroop, use = "complete.obs")
# Create plots
p1 <- ggplot(merged_data_final_score, aes(x = mean_FinalScore_Flanker, y = mean_FinalScore_Simon)) +
geom_point() +
geom_smooth(method = "lm") +
labs(title = "Relationship between Final Scores in Flanker and Simon",
x = "Final Score Flanker",
y = "Final Score Simon") +
annotate("text", x = Inf, y = Inf, label = paste("r =", round(correlation_Flanker_Simon_FinalScore, 2)), hjust = 1.1, vjust = 1.5, size = 5, color = "blue")
p2 <- ggplot(merged_data_final_score, aes(x = mean_FinalScore_Flanker, y = mean_FinalScore_Stroop)) +
geom_point() +
geom_smooth(method = "lm") +
labs(title = "Relationship between Final Scores in Flanker and Stroop",
x = "Final Score Flanker",
y = "Final Score Stroop") +
annotate("text", x = Inf, y = Inf, label = paste("r =", round(correlation_Flanker_Stroop_FinalScore, 2)), hjust = 1.1, vjust = 1.5, size = 5, color = "blue")
p3 <- ggplot(merged_data_final_score, aes(x = mean_FinalScore_Simon, y = mean_FinalScore_Stroop)) +
geom_point() +
geom_smooth(method = "lm") +
labs(title = "Relationship between Final Scores in Simon and Stroop",
x = "Final Score Simon",
y = "Final Score Stroop") +
annotate("text", x = Inf, y = Inf, label = paste("r =", round(correlation_Simon_Stroop_FinalScore, 2)), hjust = 1.1, vjust = 1.5, size = 5, color = "blue")
# Combine plots
combined_plot <- p1 + p2 + p3 + plot_layout(ncol = 1)
combined_plot
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 42 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 42 rows containing missing values or values outside the scale range
## (`geom_point()`).
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 48 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 48 rows containing missing values or values outside the scale range
## (`geom_point()`).
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 17 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 17 rows containing missing values or values outside the scale range
## (`geom_point()`).
# Save the combined plot
ggsave("combined_plot.png", plot = combined_plot, dpi = 300, width = 8, height = 12, units = "in")
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 42 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 42 rows containing missing values or values outside the scale range
## (`geom_point()`).
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 48 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 48 rows containing missing values or values outside the scale range
## (`geom_point()`).
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 17 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 17 rows containing missing values or values outside the scale range
## (`geom_point()`).
# Load necessary libraries
library(dplyr)
library(lme4)
library(ggplot2)
# Ensure Task.RT and FinalScore are numeric
MergeFlankerDec8_c <- MergeFlankerDec8_c %>% mutate(Task.RT = as.numeric(Task.RT))
MergeSimonDec8th_c <- MergeSimonDec8th_c %>% mutate(FinalScore = as.numeric(FinalScore))
# Remove rows with NA or zero values
MergeFlankerDec8_c <- MergeFlankerDec8_c %>% dplyr::filter(!is.na(Task.RT) & Task.RT > 0)
MergeSimonDec8th_c <- MergeSimonDec8th_c %>% dplyr::filter(!is.na(FinalScore) & FinalScore > 0)
# Compute the mean FinalScore for each individual in MergeSimonDec8th_c
mean_final_score_Simon <- MergeSimonDec8th_c %>%
group_by(Subject) %>%
summarise(mean_FinalScore_Simon = mean(FinalScore, na.rm = TRUE))
# Merge the mean FinalScore into MergeFlankerDec8_c
MergeFlankerDec8_c <- MergeFlankerDec8_c %>%
left_join(mean_final_score_Simon, by = "Subject")
# Standardize the mean FinalScore and Task.RT
MergeFlankerDec8_c <- MergeFlankerDec8_c %>%
mutate(mean_FinalScore_Simon = scale(mean_FinalScore_Simon, center = TRUE, scale = TRUE),
Task.RT = scale(Task.RT, center = TRUE, scale = TRUE))
# Run the linear mixed-effects model
lme_model <- lme4::lmer(Task.RT ~ mean_FinalScore_Simon + TrialType + (1 | Subject), data = MergeFlankerDec8_c)
# Print the model summary
summary(lme_model)
## Linear mixed model fit by REML ['lmerMod']
## Formula: Task.RT ~ mean_FinalScore_Simon + TrialType + (1 | Subject)
## Data: MergeFlankerDec8_c
##
## REML criterion at convergence: 18256.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.8838 -0.6375 -0.1638 0.4696 5.5249
##
## Random effects:
## Groups Name Variance Std.Dev.
## Subject (Intercept) 0.3280 0.5727
## Residual 0.5461 0.7390
## Number of obs: 7837, groups: Subject, 259
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) -0.16748 0.04038 -4.147
## mean_FinalScore_Simon -0.38526 0.03549 -10.857
## TrialTypeFullyIncongruent 0.57772 0.02374 24.338
## TrialTypeStimCongruentRespIncongruent 0.42815 0.02358 18.160
## TrialTypeStimIncongruentRespCongruent 0.37951 0.02334 16.258
##
## Correlation of Fixed Effects:
## (Intr) m_FS_S TrlTFI TTSCRI
## mn_FnlScr_S 0.207
## TrlTypFllyI -0.279 -0.010
## TrlTypStCRI -0.283 -0.011 0.486
## TrlTypStIRC -0.286 -0.006 0.490 0.493
icc(lme_model)
## # Intraclass Correlation Coefficient
##
## Adjusted ICC: 0.375
## Unadjusted ICC: 0.308
# Plot the relationship between mean FinalScore Simon and Task.RT
ggplot(MergeFlankerDec8_c, aes(x = mean_FinalScore_Simon, y = Task.RT)) +
geom_point(color = "steelblue") +
geom_smooth(method = "lm", se = FALSE, color = "red") +
theme_minimal() +
labs(title = "Relationship between Simon Final Score and Task.RT",
x = "Simon Final Score",
y = "Task.RT (Flanker Global RT)") +
theme(plot.title = element_text(hjust = 0.5))
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 83 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 83 rows containing missing values or values outside the scale range
## (`geom_point()`).
# Ensure necessary libraries are loaded
library(dplyr)
library(lme4)
library(lmerTest)
library(ggplot2)
library(performance)
# Assuming you have already preprocessed and cleaned the datasets:
# Load your datasets here if not already loaded
# MergeFlankerDec8 <- read_excel("C:/path_to_your_file/MergeFlankerDec8.xlsx")
# MergeSimonDec8th <- read_excel("C:/path_to_your_file/MergeSimonDec8th.xlsx")
# Compute the mean FinalScore for each individual in MergeSimonDec8th_c
mean_final_score_Simon <- MergeSimonDec8th_c %>%
group_by(Subject) %>%
summarise(mean_FinalScore_Simon = mean(FinalScore, na.rm = TRUE))
# Merge the Simon FinalScore into MergeFlankerDec8_c
MergeFlankerDec8_c <- MergeFlankerDec8_c %>%
left_join(mean_final_score_Simon, by = "Subject")
# Remove duplicate columns if they exist (e.g., if the dataset had duplicate joins previously)
MergeFlankerDec8_c <- MergeFlankerDec8_c %>%
select(-contains("mean_FinalScore_Simon."))
# Check for the new column
if ("mean_FinalScore_Simon" %in% colnames(MergeFlankerDec8_c)) {
# Standardize the Simon FinalScore and Task.RT
MergeFlankerDec8_c <- MergeFlankerDec8_c %>%
mutate(mean_FinalScore_Simon = scale(mean_FinalScore_Simon, center = TRUE, scale = TRUE),
Task.RT = scale(Task.RT, center = TRUE, scale = TRUE))
# Fit the linear mixed-effects model
model2 <- lme4::lmer(Task.RT ~ mean_FinalScore_Simon + TrialType + (1 | Subject), data = MergeFlankerDec8_c)
summary(model2)
# Calculate ICC for model2
icc_model2 <- performance::icc(model2)
print(icc_model2)
# Visualize the relationship between mean_FinalScore_Simon and Task.RT
ggplot(MergeFlankerDec8_c, aes(x = mean_FinalScore_Simon, y = Task.RT)) +
geom_point(color = "steelblue") +
geom_smooth(method = "lm", se = FALSE, color = "red") +
theme_minimal() +
labs(title = "Relationship between FinalScore (Simon) and Task.RT (Flanker)",
x = "FinalScore (Simon)",
y = "Task.RT (Flanker)") +
theme(plot.title = element_text(hjust = 0.5))
} else {
print("The mean_FinalScore_Simon column does not exist in the merged dataset.")
}
## [1] "The mean_FinalScore_Simon column does not exist in the merged dataset."