## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  message = FALSE,
  warning = FALSE
)

## ----setup--------------------------------------------------------------------
library(mariposa)
library(dplyr)
data(survey_data)

## -----------------------------------------------------------------------------
survey_data <- rec(survey_data, age,
  rules = "18:29=1 [Young]; 30:49=2 [Middle]; 50:99=3 [Older]",
  suffix = "_group", as_factor = TRUE
)

frequency(survey_data, age_group)

## -----------------------------------------------------------------------------
survey_data <- rec(survey_data, trust_government,
  rules = "rev", suffix = "_rev"
)

# Original: 1=low trust ... 5=high trust
# Reversed: 1=high trust ... 5=low trust
head(data.frame(
  original = survey_data$trust_government,
  reversed = survey_data$trust_government_rev
))

## -----------------------------------------------------------------------------
survey_data <- rec(survey_data, income,
  rules = "dicho", suffix = "_dicho"
)

frequency(survey_data, income_dicho)

## -----------------------------------------------------------------------------
# Split at the mean
survey_data <- rec(survey_data, income,
  rules = "mean", suffix = "_mean_split"
)

# Split at a fixed cut-point
survey_data <- rec(survey_data, income,
  rules = "dicho(3000)", suffix = "_custom"
)

## -----------------------------------------------------------------------------
survey_data <- rec(survey_data, education,
  rules = "1:2=1 [Lower]; else=2 [Higher]",
  suffix = "_binary", as_factor = TRUE
)

frequency(survey_data, education_binary)

## -----------------------------------------------------------------------------
# Create dummy variables for region
dummies <- to_dummy(survey_data, region, append = FALSE)
head(dummies)

## -----------------------------------------------------------------------------
dummies <- to_dummy(survey_data, gender, suffix = "label", append = FALSE)
head(dummies)

## -----------------------------------------------------------------------------
dummies <- to_dummy(survey_data, education, ref = 1, append = FALSE)
head(dummies)

## ----eval = FALSE-------------------------------------------------------------
# survey_data <- to_dummy(survey_data, gender, suffix = "label")
# # Adds gender_Male, gender_Female to the data frame

## -----------------------------------------------------------------------------
survey_data <- survey_data %>%
  std(age, income)

# Check: mean ≈ 0, sd ≈ 1
survey_data %>%
  describe(age, income, show = c("mean", "sd"))

## -----------------------------------------------------------------------------
# Default: divide by SD
survey_data_methods <- survey_data %>%
  std(life_satisfaction, method = "sd", suffix = "_sd") %>%
  std(life_satisfaction, method = "2sd", suffix = "_2sd") %>%
  std(life_satisfaction, method = "mad", suffix = "_mad")

survey_data_methods %>%
  describe(life_satisfaction_sd, life_satisfaction_2sd, life_satisfaction_mad,
           show = c("mean", "sd"))

## -----------------------------------------------------------------------------
survey_data <- survey_data %>%
  std(income, weights = sampling_weight, suffix = "_wstd")

survey_data %>%
  describe(income_wstd, show = c("mean", "sd"))

## -----------------------------------------------------------------------------
survey_data <- survey_data %>%
  group_by(region) %>%
  std(income, suffix = "_gstd") %>%
  ungroup()

## -----------------------------------------------------------------------------
survey_data <- survey_data %>%
  center(age, income, suffix = "_c")

survey_data %>%
  describe(age_c, income_c, show = c("mean", "sd", "min", "max"))

## -----------------------------------------------------------------------------
survey_data <- survey_data %>%
  group_by(region) %>%
  center(income, suffix = "_gc") %>%
  ungroup()

# Group means are now zero within each region
survey_data %>%
  group_by(region) %>%
  describe(income_gc, show = c("mean", "sd"))

## -----------------------------------------------------------------------------
survey_data <- survey_data %>%
  center(age, weights = sampling_weight, suffix = "_wc")

## -----------------------------------------------------------------------------
survey_data <- survey_data %>%
  mutate(m_trust = row_means(., trust_government, trust_media, trust_science))

survey_data %>%
  describe(m_trust)

## -----------------------------------------------------------------------------
survey_data <- survey_data %>%
  mutate(m_trust2 = row_means(., starts_with("trust")))

## -----------------------------------------------------------------------------
survey_data <- survey_data %>%
  mutate(m_trust3 = row_means(
    pick(trust_government, trust_media, trust_science)
  ))

## -----------------------------------------------------------------------------
survey_data <- survey_data %>%
  mutate(m_trust_strict = row_means(
    ., trust_government, trust_media, trust_science,
    min_valid = 2
  ))

## -----------------------------------------------------------------------------
survey_data <- survey_data %>%
  mutate(trust_total = row_sums(., trust_government, trust_media, trust_science))

survey_data %>%
  describe(trust_total)

## -----------------------------------------------------------------------------
# How many trust items did each person rate as 5 (highest)?
survey_data <- survey_data %>%
  mutate(n_high_trust = row_count(
    ., trust_government, trust_media, trust_science,
    count = 5
  ))

frequency(survey_data, n_high_trust)

## -----------------------------------------------------------------------------
survey_data <- survey_data %>%
  mutate(trust_pomps = pomps(m_trust, scale_min = 1, scale_max = 5))

survey_data %>%
  describe(trust_pomps)

## -----------------------------------------------------------------------------
# Transform multiple variables at once
survey_data <- survey_data %>%
  mutate(across(
    c(trust_government, trust_media, trust_science),
    ~ pomps(.x, scale_min = 1, scale_max = 5),
    .names = "{.col}_pomps"
  ))

## -----------------------------------------------------------------------------
data(survey_data)  # fresh copy

# 1. Recode: create age groups and reverse-code an item
survey_data <- rec(survey_data, age,
  rules = "18:29=1 [Young]; 30:49=2 [Middle]; 50:99=3 [Older]",
  suffix = "_group", as_factor = TRUE)
survey_data <- rec(survey_data, trust_government,
  rules = "rev", suffix = "_rev")

# 2. Create scale score
survey_data <- survey_data %>%
  mutate(m_trust = row_means(., trust_government, trust_media, trust_science,
                             min_valid = 2))

# 3. Standardize for regression
survey_data <- survey_data %>%
  std(age, income, suffix = "_z")

# 4. Use in analysis
survey_data %>%
  t_test(m_trust, group = gender, weights = sampling_weight)

survey_data %>%
  linear_regression(life_satisfaction ~ age_z + income_z + m_trust,
                    weights = sampling_weight)