Figure-2.R

# load pacakages 
library(tidyverse) # used to clean, manipulate and visualise data 

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

# Read the raw data file 
data <- read_csv(file = "/cloud/project/Study 8 data.csv")

## Rows: 373 Columns: 340
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (340): StartDate, EndDate, Status, IPAddress, Progress, Duration (in sec...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

# Remove row one and two for clarity 
data <- data[-c(1, 2), ] 

# Apply exclusion critera 
# remove participants who responded twice and keep only first response
# Use Prolific_PID variable 
duplicates <- data %>%
  count(Prolific_PID) %>%
  filter(n > 1) %>%
  pull(Prolific_PID) # Will identify P's that appear more than once
data <- data %>%
  group_by(Prolific_PID) %>%
  slice(1) %>%
  ungroup() # Keep only the first occurrence that appears
# Remove participants who did not consent 
data <- data %>%
  filter(Consent == 1, na.rm = TRUE)
# remove participants who were not serious 
data <- data %>%
  filter(Serious_check == 1, na.rm = TRUE)
# remove participants who did not complete 
data <- data %>%
  filter(Finished == 1, na.rm = TRUE)
# remove participants who failed attention check 
data <- data %>%
  filter(SC0 >= 4)

# rename condition variable 
colnames(data)[colnames(data)=="FL_10_DO"] <- "condition"

# make dataframe for FIGURE 2 HISTOGRAM 
figure2 <- data %>% 
  group_by(condition, advancement) %>% 
  summarise(n=n())

## `summarise()` has grouped output by 'condition'. You can override using the
## `.groups` argument.

# recode condition titles 
figure2 <- figure2 %>% 
  mutate(condition = recode(condition, 
                            'Block_1_Generic_Conflict' = 'Conflicting/Generic',
                            'Block_3_Qualified_Conflict' = 'Conflicting/Qualified',
                            'Block_2_Generic_Consistent' = 'Non-conflicing/Generic',
                            'Block_4_Qualified_Consistent' = 'Non-conflicting/Qualified'))

# recode advancement titles 
figure2 <- figure2 %>% 
  mutate(advancement = recode(advancement, 
                            '-1' = 'Less',
                            '0' = 'Same',
                            '1' = 'More'))

# Set the factor levels to ensure correct order
figure2$advancement <- factor(figure2$advancement, levels = c("Less", "Same", "More"))

# Plot the histogram
plot <- ggplot(figure2, aes(x = advancement, y = n, fill = condition)) +
  geom_bar(stat = "identity", position = "dodge") +
  scale_fill_manual(values = c("#333333", "#818181", "#ababab", "#cccccc")) +
  labs(x = "Advancement", y = "Number of Participants", fill = "Condition") +
  theme(axis.title = element_text(size = 7), # Adjust axis titles size
        axis.text = element_text(size = 6),   # Adjust axis text size
        legend.title = element_text(size = 7), # Adjust legend title size
        legend.text = element_text(size = 6))   # Adjust legend text size
print(plot)