eohi/.history/mixed anova_20250912110922.r
2025-12-23 15:47:09 -05:00

284 lines
9.2 KiB
R

# Mixed ANOVA Analysis for Past vs Future Differences
# EOHI Experiment Data Analysis
# Load required libraries
library(tidyverse)
library(ez)
library(afex)
library(emmeans)
library(ggplot2)
library(car)
# 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)
# Prepare data for mixed ANOVA
# We'll reshape the data to have Past and Future as separate rows for each participant
# Create a function to reshape data for a specific domain
reshape_domain_data <- function(data, domain_name) {
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")
return(NULL)
}
# Create long format data
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]]) %>%
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]]) %>%
select(-all_of(fut_col))
combined_data <- rbind(past_data, fut_data) %>%
mutate(TimePerspective = as.factor(TimePerspective),
pID = as.factor(pID))
return(combined_data)
}
# Define domains to analyze
domains <- 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")
# Run mixed ANOVA for each domain
results_list <- list()
for (domain in domains) {
cat("\n", "="*60, "\n")
cat("ANALYZING DOMAIN:", toupper(domain), "\n")
cat("="*60, "\n")
# Reshape data for this domain
domain_data <- reshape_domain_data(data, domain)
if (is.null(domain_data)) {
next
}
# Check for missing values
missing_count <- sum(is.na(domain_data$Difference))
if (missing_count > 0) {
cat("Warning:", missing_count, "missing values found for", domain, "\n")
domain_data <- domain_data[!is.na(domain_data$Difference), ]
}
# Descriptive statistics
cat("\nDescriptive Statistics:\n")
desc_stats <- domain_data %>%
group_by(TimePerspective) %>%
summarise(
n = n(),
mean = mean(Difference, na.rm = TRUE),
sd = sd(Difference, na.rm = TRUE),
median = median(Difference, na.rm = TRUE),
.groups = 'drop'
)
print(desc_stats)
# Effect size (Cohen's d)
past_diff <- domain_data$Difference[domain_data$TimePerspective == "Past"]
fut_diff <- domain_data$Difference[domain_data$TimePerspective == "Future"]
pooled_sd <- sqrt(((length(past_diff) - 1) * var(past_diff) +
(length(fut_diff) - 1) * var(fut_diff)) /
(length(past_diff) + length(fut_diff) - 2))
cohens_d <- (mean(past_diff) - mean(fut_diff)) / pooled_sd
cat("\nCohen's d (Past vs Future):", round(cohens_d, 5), "\n")
# Mixed ANOVA using ezANOVA
tryCatch({
# Simple repeated measures ANOVA (TimePerspective as within-subjects)
anova_result <- ezANOVA(
data = domain_data,
dv = Difference,
wid = pID,
within = TimePerspective,
between = c(GROUP, TASK_DO),
type = 3,
detailed = TRUE
)
cat("\nMixed ANOVA Results:\n")
print(anova_result)
# Store results
results_list[[domain]] <- list(
descriptive = desc_stats,
cohens_d = cohens_d,
anova = anova_result
)
# Post-hoc comparisons if significant
if (!is.null(anova_result$ANOVA)) {
if (any(anova_result$ANOVA$p < 0.05, na.rm = TRUE)) {
cat("\nSignificant effects found! Post-hoc analysis:\n")
# Pairwise comparisons for TimePerspective
if ("TimePerspective" %in% anova_result$ANOVA$Effect &&
anova_result$ANOVA$p[anova_result$ANOVA$Effect == "TimePerspective"] < 0.05) {
# Simple t-test for comparison
t_test_result <- t.test(past_diff, fut_diff, paired = TRUE)
cat("\nPaired t-test (Past vs Future):\n")
cat("t =", round(t_test_result$statistic, 3),
", df =", t_test_result$parameter,
", p =", round(t_test_result$p.value, 5), "\n")
}
}
}
}, error = function(e) {
cat("Error in ANOVA for", domain, ":", e$message, "\n")
# Fallback to simple paired t-test
t_test_result <- t.test(past_diff, fut_diff, paired = TRUE)
cat("\nFallback: Paired t-test (Past vs Future):\n")
cat("t =", round(t_test_result$statistic, 3),
", df =", t_test_result$parameter,
", p =", round(t_test_result$p.value, 5), "\n")
results_list[[domain]] <- list(
descriptive = desc_stats,
cohens_d = cohens_d,
t_test = t_test_result
)
})
}
# 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")