## -----------------------------------------------------------------------------
knitr::opts_chunk$set(
  collapse  = TRUE,
  comment   = "#>",
  message   = FALSE,
  warning   = FALSE,
  fig.align = "center"
)

## -----------------------------------------------------------------------------
# # Install from GitHub
# # install.packages("remotes")
# remotes::install_github("stalynGuerrero/complexr")

## -----------------------------------------------------------------------------
library(complexr)

## -----------------------------------------------------------------------------
data <- generate_example_data(n_upm = 100, seed = 123)
dplyr::glimpse(data)

## -----------------------------------------------------------------------------
# # CSV
# data <- read_survey_data("survey.csv")
# 
# # SPSS
# data <- read_survey_data("survey.sav")
# 
# # Stata
# data <- read_survey_data("survey.dta")
# 
# # Excel
# data <- read_survey_data("survey.xlsx")

## -----------------------------------------------------------------------------
data <- mutate_survey_data(
  data,
  definitions = list(
    log_ingreso = ~ log(ingreso_pc + 1),
    ratio_gasto = ~ gasto_pc / ingreso_pc
  )
)

dplyr::select(data, ingreso_pc, log_ingreso, ratio_gasto) |> head(4)

## -----------------------------------------------------------------------------
design <- as_survey_design_tbl(
  data    = data,
  weight  = "weight",
  strata  = "strata",
  cluster = "upm",
  nest    = TRUE
)

class(design)

## -----------------------------------------------------------------------------
describe_survey_design(design)

## -----------------------------------------------------------------------------
r_mean <- estimate_survey(
  design    = design,
  variable  = "ingreso_pc",
  estimator = "mean"
)
r_mean

## -----------------------------------------------------------------------------
r_total <- estimate_survey(
  design    = design,
  variable  = "ingreso_pc",
  estimator = "total"
)
r_total

## -----------------------------------------------------------------------------
r_pobre <- estimate_survey(
  design    = design,
  variable  = "pobre",
  estimator = "prop"
)
r_pobre

## -----------------------------------------------------------------------------
r_empleo <- estimate_survey(
  design    = design,
  variable  = "empleo",
  estimator = "prop"
)
r_empleo

## -----------------------------------------------------------------------------
r_ratio <- estimate_survey(
  design      = design,
  estimator   = "ratio",
  numerator   = "ingreso_pc",
  denominator = "gasto_pc"
)
r_ratio

## -----------------------------------------------------------------------------
r_ratio_cat <- estimate_survey(
  design          = design,
  estimator       = "ratio",
  numerator       = "empleo",
  denominator     = "empleo",
  ratio_num_level = "Formal",
  ratio_den_level = "Informal"
)
r_ratio_cat

## -----------------------------------------------------------------------------
r_ratio_mix <- estimate_survey(
  design          = design,
  estimator       = "ratio",
  numerator       = "ingreso_pc",
  denominator     = "empleo",
  ratio_den_level = "Formal"
)
r_ratio_mix

## -----------------------------------------------------------------------------
r_quant <- estimate_survey(
  design    = design,
  variable  = "ingreso_pc",
  estimator = "quantile",
  probs     = c(0.10, 0.25, 0.50, 0.75, 0.90)
)
r_quant

## -----------------------------------------------------------------------------
r_region <- estimate_survey(
  design    = design,
  variable  = "ingreso_pc",
  estimator = "mean",
  by        = "region"
)
r_region

## -----------------------------------------------------------------------------
r_region_area <- estimate_survey(
  design    = design,
  variable  = "ingreso_pc",
  estimator = "mean",
  by        = c("region", "area")
)
r_region_area

## -----------------------------------------------------------------------------
r_pobre_region <- estimate_survey(
  design    = design,
  variable  = "pobre",
  estimator = "prop",
  by        = "region"
)
r_pobre_region

## -----------------------------------------------------------------------------
format_results_table(r_region, digits = 3)

## -----------------------------------------------------------------------------
plot_results_bar(r_region)

## -----------------------------------------------------------------------------
plot_results_bar(r_region_area)

## -----------------------------------------------------------------------------
plot_results_bar(r_pobre_region)

## -----------------------------------------------------------------------------
# ComplexSurvey_app()

## -----------------------------------------------------------------------------
library(complexr)

# 1. Generate / load data
data <- generate_example_data(n_upm = 100, seed = 2024)

# 2. Derive new variables
data <- mutate_survey_data(
  data,
  definitions = list(
    log_ingreso = ~ log(ingreso_pc + 1)
  )
)

# 3. Build survey design (stratified multistage)
design <- as_survey_design_tbl(
  data    = data,
  weight  = "weight",
  strata  = "strata",
  cluster = "upm",
  nest    = TRUE
)

# 4. Diagnose: N_hat, H, PSUs, CV(w)
describe_survey_design(design)

# 5. Estimate domain mean and format
res <- estimate_survey(
  design    = design,
  variable  = "ingreso_pc",
  estimator = "mean",
  by        = c("region", "area")
)

format_results_table(res, digits = 2)