139 lines
5.6 KiB
R
139 lines
5.6 KiB
R
# Mixed ANOVA Analysis for Domain Means - EOHI2
|
|
# EOHI Experiment Data Analysis - Domain Level Analysis with INTERVAL factor
|
|
# Variables: NPast_5_pref_MEAN, NPast_5_pers_MEAN, NPast_5_val_MEAN, etc.
|
|
# NFut_5_pref_MEAN, NFut_5_pers_MEAN, NFut_5_val_MEAN, etc.
|
|
# NPast_10_pref_MEAN, NPast_10_pers_MEAN, NPast_10_val_MEAN, etc.
|
|
# NFut_10_pref_MEAN, NFut_10_pers_MEAN, NFut_10_val_MEAN, etc.
|
|
# 5.10past_pref_MEAN, 5.10past_pers_MEAN, 5.10past_val_MEAN
|
|
# 5.10fut_pref_MEAN, 5.10fut_pers_MEAN, 5.10fut_val_MEAN
|
|
|
|
# Load required libraries
|
|
library(tidyverse)
|
|
library(ez)
|
|
library(car)
|
|
library(afex) # For aov_ez (cleaner ANOVA output)
|
|
library(nortest) # For normality tests
|
|
library(emmeans) # For post-hoc comparisons
|
|
library(purrr) # For map functions
|
|
library(effsize) # For Cohen's d calculations
|
|
library(effectsize) # For effect size calculations
|
|
|
|
# Global options to remove scientific notation
|
|
options(scipen = 999)
|
|
|
|
# Set contrasts to sum for mixed ANOVA (necessary for proper interpretation)
|
|
options(contrasts = c("contr.sum", "contr.poly"))
|
|
|
|
setwd("C:/Users/irina/Documents/DND/EOHI/eohi2")
|
|
|
|
# Read the data
|
|
data <- read.csv("eohi2.csv")
|
|
|
|
# Display basic information about the dataset
|
|
print(paste("Dataset dimensions:", paste(dim(data), collapse = " x")))
|
|
print(paste("Number of participants:", length(unique(data$ResponseId))))
|
|
|
|
# Verify the specific variables we need
|
|
required_vars <- c("NPast_5_pref_MEAN", "NPast_5_pers_MEAN", "NPast_5_val_MEAN",
|
|
"NPast_10_pref_MEAN", "NPast_10_pers_MEAN", "NPast_10_val_MEAN",
|
|
"NFut_5_pref_MEAN", "NFut_5_pers_MEAN", "NFut_5_val_MEAN",
|
|
"NFut_10_pref_MEAN", "NFut_10_pers_MEAN", "NFut_10_val_MEAN",
|
|
"5.10past_pref_MEAN", "5.10past_pers_MEAN", "5.10past_val_MEAN",
|
|
"5.10fut_pref_MEAN", "5.10fut_pers_MEAN", "5.10fut_val_MEAN")
|
|
|
|
missing_vars <- required_vars[!required_vars %in% colnames(data)]
|
|
if (length(missing_vars) > 0) {
|
|
print(paste("Warning: Missing variables:", paste(missing_vars, collapse = ", ")))
|
|
} else {
|
|
print("All required domain mean variables found!")
|
|
}
|
|
|
|
# Define domain mapping with TIME, DOMAIN, and INTERVAL factors
|
|
domain_mapping <- data.frame(
|
|
variable = required_vars,
|
|
time = c(rep("Past", 3), rep("Past", 3), rep("Future", 3), rep("Future", 3),
|
|
rep("Past", 3), rep("Future", 3)),
|
|
domain = rep(c("Preferences", "Personality", "Values"), 6),
|
|
interval = c(rep("5", 3), rep("10", 3), rep("5", 3), rep("10", 3),
|
|
rep("5_10", 3), rep("5_10", 3)),
|
|
stringsAsFactors = FALSE
|
|
)
|
|
|
|
print("Domain mapping created:")
|
|
print(domain_mapping)
|
|
|
|
# Efficient data pivoting using pivot_longer
|
|
long_data <- data %>%
|
|
select(ResponseId, TEMPORAL_DO, INTERVAL_DO, all_of(required_vars)) %>%
|
|
pivot_longer(
|
|
cols = all_of(required_vars),
|
|
names_to = "variable",
|
|
values_to = "MEAN_DIFFERENCE"
|
|
) %>%
|
|
left_join(domain_mapping, by = "variable") %>%
|
|
# Convert to factors with proper levels
|
|
mutate(
|
|
TIME = factor(time, levels = c("Past", "Future")),
|
|
DOMAIN = factor(domain, levels = c("Preferences", "Personality", "Values")),
|
|
INTERVAL = factor(interval, levels = c("5", "10", "5_10")),
|
|
ResponseId = as.factor(ResponseId),
|
|
TEMPORAL_DO = as.factor(TEMPORAL_DO),
|
|
INTERVAL_DO = as.factor(INTERVAL_DO)
|
|
) %>%
|
|
# Select final columns and remove any rows with missing values
|
|
select(ResponseId, TEMPORAL_DO, INTERVAL_DO, TIME, DOMAIN, INTERVAL, MEAN_DIFFERENCE) %>%
|
|
filter(!is.na(MEAN_DIFFERENCE))
|
|
|
|
print(paste("Long data dimensions:", paste(dim(long_data), collapse = " x")))
|
|
print(paste("Number of participants:", length(unique(long_data$ResponseId))))
|
|
|
|
# =============================================================================
|
|
# DESCRIPTIVE STATISTICS
|
|
# =============================================================================
|
|
|
|
# Overall descriptive statistics by TIME, DOMAIN, and INTERVAL
|
|
desc_stats <- long_data %>%
|
|
group_by(TIME, DOMAIN, INTERVAL) %>%
|
|
summarise(
|
|
n = n(),
|
|
mean = round(mean(MEAN_DIFFERENCE, na.rm = TRUE), 5),
|
|
variance = round(var(MEAN_DIFFERENCE, na.rm = TRUE), 5),
|
|
sd = round(sd(MEAN_DIFFERENCE, na.rm = TRUE), 5),
|
|
median = round(median(MEAN_DIFFERENCE, na.rm = TRUE), 5),
|
|
q1 = round(quantile(MEAN_DIFFERENCE, 0.25, na.rm = TRUE), 5),
|
|
q3 = round(quantile(MEAN_DIFFERENCE, 0.75, na.rm = TRUE), 5),
|
|
min = round(min(MEAN_DIFFERENCE, na.rm = TRUE), 5),
|
|
max = round(max(MEAN_DIFFERENCE, na.rm = TRUE), 5),
|
|
.groups = 'drop'
|
|
)
|
|
|
|
print("Descriptive statistics by TIME, DOMAIN, and INTERVAL:")
|
|
print(desc_stats)
|
|
|
|
# Descriptive statistics by between-subjects factors
|
|
desc_stats_by_between <- long_data %>%
|
|
group_by(TEMPORAL_DO, INTERVAL_DO, TIME, DOMAIN, INTERVAL) %>%
|
|
summarise(
|
|
n = n(),
|
|
mean = round(mean(MEAN_DIFFERENCE, na.rm = TRUE), 5),
|
|
variance = round(var(MEAN_DIFFERENCE, na.rm = TRUE), 5),
|
|
sd = round(sd(MEAN_DIFFERENCE, na.rm = TRUE), 5),
|
|
.groups = 'drop'
|
|
)
|
|
|
|
print("Descriptive statistics by between-subjects factors:")
|
|
print(desc_stats_by_between)
|
|
|
|
# Summary by between-subjects factors only
|
|
desc_stats_between_only <- long_data %>%
|
|
group_by(TEMPORAL_DO, INTERVAL_DO) %>%
|
|
summarise(
|
|
n = n(),
|
|
mean = round(mean(MEAN_DIFFERENCE, na.rm = TRUE), 5),
|
|
variance = round(var(MEAN_DIFFERENCE, na.rm = TRUE), 5),
|
|
sd = round(sd(MEAN_DIFFERENCE, na.rm = TRUE), 5),
|
|
.groups = 'drop'
|
|
)
|
|
|
|
print("Descriptive statistics by between-subjects factors only:")
|
|
print(desc_stats_between_only) |