eohi/.history/mixed anova_20250912111750.r
2025-12-23 15:47:09 -05:00

317 lines
10 KiB
R

# Mixed ANOVA Analysis for Past vs Future Differences
# EOHI Experiment Data Analysis
# Load required libraries
library(tidyverse)
library(ez)
library(car)
library(nortest) # For normality tests
# Read the data
data <- read.csv("eohi1/exp1.csv")
# Display basic information about the dataset
cat("Dataset dimensions:", dim(data), "\n")
cat("Number of participants:", length(unique(data$pID)), "\n")
# Check experimental conditions
cat("\nExperimental conditions:\n")
table(data$GROUP, data$TASK_DO, data$TEMPORAL_DO)
# STEP 1: PROPER DATA RESHAPING
# Define domains with their categories
domain_info <- data.frame(
domain = c("pref_read", "pref_music", "pref_tv", "pref_nap", "pref_travel",
"pers_extravert", "pers_critical", "pers_dependable", "pers_anxious", "pers_complex",
"val_obey", "val_trad", "val_opinion", "val_performance", "val_justice",
"life_ideal", "life_excellent", "life_satisfied", "life_important", "life_change"),
domain_type = c(rep("Preferences", 5),
rep("Personality", 5),
rep("Values", 5),
rep("Life_Satisfaction", 5)),
stringsAsFactors = FALSE
)
# Function to reshape ALL domains at once with domain information
reshape_all_domains <- function(data, domain_info) {
all_long_data <- data.frame()
for (i in 1:nrow(domain_info)) {
domain_name <- domain_info$domain[i]
domain_type <- domain_info$domain_type[i]
past_col <- paste0("NPastDiff_", domain_name)
fut_col <- paste0("NFutDiff_", domain_name)
# Check if columns exist
if (!(past_col %in% colnames(data)) || !(fut_col %in% colnames(data))) {
cat("Warning: Columns", past_col, "or", fut_col, "not found\n")
next
}
# Create long format data for this domain
past_data <- data %>%
select(pID, ResponseId, GROUP, TASK_DO, TEMPORAL_DO, ITEM_DO, COC_DO,
demo_sex, demo_age_1, AOT_total, CRT_correct, all_of(past_col)) %>%
mutate(
TimePerspective = "Past",
Difference = .data[[past_col]],
Domain_Type = domain_type, # e.g., "Preferences"
Domain_Item = domain_name # e.g., "pref_read"
) %>%
select(-all_of(past_col))
fut_data <- data %>%
select(pID, ResponseId, GROUP, TASK_DO, TEMPORAL_DO, ITEM_DO, COC_DO,
demo_sex, demo_age_1, AOT_total, CRT_correct, all_of(fut_col)) %>%
mutate(
TimePerspective = "Future",
Difference = .data[[fut_col]],
Domain_Type = domain_type,
Domain_Item = domain_name
) %>%
select(-all_of(fut_col))
# Combine past and future data for this domain
domain_long_data <- rbind(past_data, fut_data)
all_long_data <- rbind(all_long_data, domain_long_data)
}
# Convert to factors
all_long_data <- all_long_data %>%
mutate(
TimePerspective = as.factor(TimePerspective),
Domain_Type = as.factor(Domain_Type),
Domain_Item = as.factor(Domain_Item),
pID = as.factor(pID)
)
return(all_long_data)
}
# Reshape all data to long format
cat("\nReshaping data to long format...\n")
long_data <- reshape_all_domains(data, domain_info)
cat("Long format data dimensions:", dim(long_data), "\n")
cat("Unique domains:", length(unique(long_data$Domain_Item)), "\n")
cat("Domain types:", unique(long_data$Domain_Type), "\n")
# STEP 2: ASSUMPTION CHECKING
cat("\n", "="*80, "\n")
cat("STEP 2: CHECKING ASSUMPTIONS\n")
cat("="*80, "\n")
# 2.1 Check for missing values
missing_summary <- long_data %>%
group_by(Domain_Type, Domain_Item, TimePerspective) %>%
summarise(
n_total = n(),
n_missing = sum(is.na(Difference)),
pct_missing = round(100 * n_missing / n_total, 2),
.groups = 'drop'
)
cat("\nMissing values by domain and time perspective:\n")
print(missing_summary)
# Remove missing values
long_data_clean <- long_data[!is.na(long_data$Difference), ]
cat("\nData after removing missing values:", dim(long_data_clean), "\n")
# 2.2 Outlier detection
cat("\nChecking for outliers...\n")
outlier_summary <- long_data_clean %>%
group_by(Domain_Type, Domain_Item, TimePerspective) %>%
summarise(
n = n(),
mean = mean(Difference),
sd = sd(Difference),
q1 = quantile(Difference, 0.25),
q3 = quantile(Difference, 0.75),
iqr = q3 - q1,
lower_bound = q1 - 1.5 * iqr,
upper_bound = q3 + 1.5 * iqr,
n_outliers = sum(Difference < lower_bound | Difference > upper_bound),
.groups = 'drop'
)
cat("Outlier summary (IQR method):\n")
print(outlier_summary)
# 2.3 Normality tests
cat("\nTesting normality...\n")
normality_results <- long_data_clean %>%
group_by(Domain_Type, Domain_Item, TimePerspective) %>%
summarise(
n = n(),
shapiro_p = ifelse(n >= 3 & n <= 5000,
shapiro.test(Difference)$p.value,
NA),
anderson_p = ifelse(n >= 7,
ad.test(Difference)$p.value,
NA),
.groups = 'drop'
) %>%
mutate(
shapiro_normal = shapiro_p > 0.05,
anderson_normal = anderson_p > 0.05,
overall_normal = case_when(
!is.na(shapiro_p) & !is.na(anderson_p) ~ shapiro_normal & anderson_normal,
!is.na(shapiro_p) ~ shapiro_normal,
!is.na(anderson_p) ~ anderson_normal,
TRUE ~ NA
)
)
cat("Normality test results:\n")
print(normality_results)
# 2.4 Homogeneity of variance (Levene's test)
cat("\nTesting homogeneity of variance...\n")
homogeneity_results <- long_data_clean %>%
group_by(Domain_Type, Domain_Item) %>%
summarise(
levene_p = leveneTest(Difference ~ TimePerspective)$`Pr(>F)`[1],
homogeneous = levene_p > 0.05,
.groups = 'drop'
)
cat("Homogeneity of variance results:\n")
print(homogeneity_results)
# STEP 3: DESCRIPTIVE STATISTICS
cat("\n", "="*80, "\n")
cat("STEP 3: DESCRIPTIVE STATISTICS\n")
cat("="*80, "\n")
desc_stats <- long_data_clean %>%
group_by(Domain_Type, Domain_Item, TimePerspective) %>%
summarise(
n = n(),
mean = mean(Difference),
sd = sd(Difference),
median = median(Difference),
q1 = quantile(Difference, 0.25),
q3 = quantile(Difference, 0.75),
min = min(Difference),
max = max(Difference),
.groups = 'drop'
)
cat("Descriptive statistics:\n")
print(desc_stats)
# Summary of all results
cat("\n", "="*80, "\n")
cat("SUMMARY OF ALL DOMAINS\n")
cat("="*80, "\n")
summary_df <- data.frame(
Domain = character(),
Past_Mean = numeric(),
Future_Mean = numeric(),
Cohen_d = numeric(),
Significant = logical(),
stringsAsFactors = FALSE
)
for (domain in names(results_list)) {
result <- results_list[[domain]]
past_mean <- result$descriptive$mean[result$descriptive$TimePerspective == "Past"]
fut_mean <- result$descriptive$mean[result$descriptive$TimePerspective == "Future"]
cohens_d <- result$cohens_d
# Check if significant (p < 0.05)
significant <- FALSE
if (!is.null(result$anova) && !is.null(result$anova$ANOVA)) {
if ("TimePerspective" %in% result$anova$ANOVA$Effect) {
p_val <- result$anova$ANOVA$p[result$anova$ANOVA$Effect == "TimePerspective"]
significant <- !is.na(p_val) && p_val < 0.05
}
} else if (!is.null(result$t_test)) {
significant <- result$t_test$p.value < 0.05
}
summary_df <- rbind(summary_df, data.frame(
Domain = domain,
Past_Mean = round(past_mean, 3),
Future_Mean = round(fut_mean, 3),
Cohen_d = round(cohens_d, 5),
Significant = significant
))
}
# Sort by effect size (absolute value)
summary_df <- summary_df[order(abs(summary_df$Cohen_d), decreasing = TRUE), ]
print(summary_df)
# Create visualization
library(ggplot2)
# Prepare data for plotting
plot_data <- summary_df %>%
mutate(
Effect_Size = abs(Cohen_d),
Direction = ifelse(Cohen_d > 0, "Past > Future", "Future > Past"),
Domain_Type = case_when(
grepl("pref_", Domain) ~ "Preferences",
grepl("pers_", Domain) ~ "Personality",
grepl("val_", Domain) ~ "Values",
grepl("life_", Domain) ~ "Life Satisfaction",
TRUE ~ "Other"
)
)
# Effect size plot
p1 <- ggplot(plot_data, aes(x = reorder(Domain, Effect_Size), y = Effect_Size,
fill = Direction, alpha = Significant)) +
geom_col() +
coord_flip() +
scale_alpha_manual(values = c(0.5, 1), name = "Significant\n(p < 0.05)") +
scale_fill_manual(values = c("Past > Future" = "#E74C3C", "Future > Past" = "#3498DB")) +
labs(
title = "Effect Sizes: Past vs Future Differences",
subtitle = "Absolute Cohen's d values across domains",
x = "Domain",
y = "|Cohen's d|",
fill = "Direction"
) +
theme_minimal() +
theme(axis.text.y = element_text(size = 8))
print(p1)
# Mean differences plot
plot_data_long <- summary_df %>%
select(Domain, Past_Mean, Future_Mean) %>%
pivot_longer(cols = c(Past_Mean, Future_Mean),
names_to = "TimePerspective",
values_to = "Mean_Difference") %>%
mutate(TimePerspective = gsub("_Mean", "", TimePerspective))
p2 <- ggplot(plot_data_long, aes(x = reorder(Domain, Mean_Difference),
y = Mean_Difference,
fill = TimePerspective)) +
geom_col(position = "dodge") +
coord_flip() +
scale_fill_manual(values = c("Past" = "#E74C3C", "Future" = "#3498DB")) +
labs(
title = "Mean Differences by Time Perspective",
subtitle = "Past vs Future difference scores",
x = "Domain",
y = "Mean Difference Score",
fill = "Time Perspective"
) +
theme_minimal() +
theme(axis.text.y = element_text(size = 8))
print(p2)
cat("\nAnalysis complete! Check the plots and summary table above.\n")
cat("Key findings:\n")
cat("- Domains with largest effect sizes:", paste(head(summary_df$Domain, 3), collapse = ", "), "\n")
cat("- Number of significant differences:", sum(summary_df$Significant), "out of", nrow(summary_df), "\n")