# Load the four data files and only keep the useful columns
prolific_export = read_csv("../data/prolific_export.csv") %>%
select(participant_id,
entered_code,
time_taken,
age,
country = `Current Country of Residence`,
sex = Sex)
results = read_csv("../data/results.csv") %>%
select(participant_id,
fund_allocation_southeast_asia = fundAllocation_UNHCR,
fund_allocation_middle_east = fundAllocation_IOM,
donation_allocation_southeast_asia = donationAllocation) %>%
mutate(fund_allocation_difference = fund_allocation_southeast_asia - fund_allocation_middle_east)
excluded = read_csv("../data/excluded.csv") %>%
select(participant_id,
failed_attention_check,
reloaded) %>%
mutate(participant_id = as.character(participant_id)) # necessary if all are NAs
agreed = read_csv("../data/all_who_agreed.csv") %>%
select(participant_id,
condition)
# Join the four datasets and clean up a bit
data_all = agreed %>%
left_join(excluded, by = "participant_id") %>%
left_join(prolific_export, by = "participant_id") %>%
full_join(results, by = "participant_id") %>%
subset(!participant_id %in% exclude_participant_ids) %>%
mutate(failed_attention_check = coalesce(failed_attention_check, 0), # replace NAs with zeros
reloaded = coalesce(reloaded, 0))
# Clean up possibly serious anomalies in the data and issue warnings if necessary
data_all_original = data_all
data_all = data_all %>%
drop_na(participant_id, condition) %>%
distinct(participant_id, .keep_all= TRUE)
# if (nrow(data_all) != nrow(data_all_original)) {
# cat("WARNING -- Data has duplicate participants, missing participant IDs, or missing conditions:")
# anti_join(data_all_original, data_all)
# }
# Create another dataset with completed submissions only
data = data_all %>%
filter(entered_code == completion_code)
# Split datasets according to the condition
data_all_rich_first = data_all %>% filter(condition == "richFirst")
data_all_poor_first = data_all %>% filter(condition == "poorFirst")
data_rich_first = data %>% filter(condition == "richFirst")
data_poor_first = data %>% filter(condition == "poorFirst")
Data
The final dataset has 64 participants in the rich first condition and 64 in the poor first condition.
We use Cohenโs d and probability of superiority as standardized effect sizes. We interpret the effect sizes based on the work of Lakens (2013).
- Lakens, D. (2013). Calculating and reporting effect sizes to facilitate cumulative science: a practical primer for t-tests and ANOVAs. Frontiers in psychology, 4, 863.
Primary effect
DV1 = standardized mean difference between funds allocated to the rich visualization and the poor visualization
DV1_rich = c(data_rich_first %>% pull(fund_allocation_southeast_asia),
data_poor_first %>% pull(fund_allocation_middle_east))
DV1_poor = c(data_rich_first %>% pull(fund_allocation_middle_east),
data_poor_first %>% pull(fund_allocation_southeast_asia))
effect1.d = cohen.d(DV1_rich, DV1_poor)
effect1.ps = ps(effect1.d)
print_effect("Cohen's d", effect1.d)
print_effect("Probability of superiority", effect1.ps, plot = F)
## Cohen's d : 0.12, 95% CI [-0.13, 0.37]
## Probability of superiority : 0.53, 95% CI [0.46, 0.6]
There is a 53.4% probability that an individual allocated more funds when s/he saw the rich visualization than the poor one.
Secondary effect
DV2 = Percentage of global UNHCR funds allocated to SouthEast Asia (the rest being allocated to other parts of the world)
DV2_rich = data_rich_first %>% pull(fund_allocation_southeast_asia)
DV2_poor = data_poor_first %>% pull(fund_allocation_southeast_asia)
effect2.d = cohen.d(DV2_rich, DV2_poor)
effect2.ps = ps(effect2.d)
print_effect("Cohen's d", effect2.d)
print_effect("Probability of superiority", effect2.ps, plot = F)
## Cohen's d : 0.18, 95% CI [-0.17, 0.53]
## Probability of superiority : 0.55, 95% CI [0.45, 0.65]
There is a 55.02% probability that a randomly sampled person who saw the rich visualization will allocate more funds than a randomly sampled person who saw the poor visualization.
DV3 = Percentage of personal money donated to the rich visualization compared to the amount donated to the poor visualization scenario
DV3_rich = c(data_rich_first %>% pull(donation_allocation_southeast_asia),
data_poor_first %>%
mutate(donation_allocation_middle_east = 100 - donation_allocation_southeast_asia) %>%
pull(donation_allocation_middle_east))
DV3_poor = c(data_rich_first %>%
mutate(donation_allocation_middle_east = 100 - donation_allocation_southeast_asia) %>%
pull(donation_allocation_middle_east),
data_poor_first %>% pull(donation_allocation_southeast_asia))
effect3.d = cohen.d(DV3_rich, DV3_poor)
effect3.ps = ps(effect3.d)
print_effect("Cohen's d", effect3.d)
print_effect("Probability of superiority", effect3.ps, plot = F)
## Cohen's d : -0.12, 95% CI [-0.37, 0.13]
## Probability of superiority : 0.47, 95% CI [0.4, 0.54]
There is a 46.6% probability that an individual donated more money to the organization related to the rich visualization.
plotAllCIs(lim = c(-1, 1), xlabel = "Percent increase in donations for information-rich visualizations")
