sdcInitial@risk$ldiversity[,'Health_Distinct_Ldiversity']
ldive <- sdcInitial@risk$ldiversity[,'Health_Distinct_Ldiversity']
dados3 <- cbind(dados2, ldive)
View(dados2)
View(dados3)
View(dados3)
library(sdcMicro)
No <- c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)
Residence <- c("Urban", "Urban", "Urban", "Urban", "Rural", "Urban", "Urban", "Urban", "Urban", "Urban")
Gender <- c("Female", "Female", "Female", "Male", "Female", "Male", "Female", "Male", "Female", "Female")
Education_level <- c("Secondary incomplete", "Secondary incomplete", "Primary incomplete", "Secondary complete", "Secondary complete", "Secondary complete", "Primary complete", "Post-secondary", "Secondary incomplete", "Secondary incomplete")
Labor_status <- c("Employed", "Employed", "Non-LF", "Employed", "Unemployed", "Employed", "Non-LF", "Unemployed", "Non-LF", "Non-LF")
Health <- c("yes", "yes", "yes", "yes", "yes", "no", "no", "yes", "no", "yes")
Weight <- c(180, 180, 215, 76, 186, 76, 180, 215, 186, 76)
# fk <- c(2, 2, 1, 2, 1, 2, 1, 1, 2, 2)
# Fk <- c(360, 360, 215, 152, 186, 152, 180, 215, 262, 262)
# risk <- c(0.0054, 0.0054, 0.0251, 0.0126, 0.0282, 0.0126, 0.0290, 0.0251, 0.0074, 0.0074)
dados <- data.frame(No, Residence, Gender, Education_level, Labor_status, Health, Weight)
selectedKeyVars = c('Residence', 'Gender', 'Education_level', 'Labor_status')
selectedWeightVar = c('Weight')
selectedSensibleVar = c('Health')
sdcInitial <- createSdcObj(dat  = dados,
keyVars     = selectedKeyVars,
# ghostVars   = selectedGhostVars,
# numVar      = selectedNumVar,
weightVar   = selectedWeightVar,
# pramVars    = selectedPramVars,
# hhId        = selectedHouseholdID,
# strataVar   = selectedStrataVar,
sensibleVar = selectedSensibleVar)
sdcInitial@risk
risk <- sdcInitial@risk$individual
dados2 <- cbind(dados, risk)
dados2$kAnon <- dados2$fk + 1
print(sdcInitial, 'kAnon')
sum(sdcInitial@risk$individual[,2] < 5)
sdcInitial <- ldiversity(obj = sdcInitial, ldiv_index = c("Health"))
sdcInitial@risk$ldiversity
sdcInitial@risk$ldiversity[,'Health_Distinct_Ldiversity']
ldive <- sdcInitial@risk$ldiversity[,'Health_Distinct_Ldiversity']
dados3 <- cbind(dados2, ldive)
View(dados3)
print(sdcInitial, 'kAnon')
View(dados3)
library(sdcMicro)
No <- c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)
Residence <- c("Urban", "Urban", "Urban", "Urban", "Rural", "Urban", "Urban", "Urban", "Urban", "Urban")
Gender <- c("Female", "Female", "Female", "Male", "Female", "Male", "Female", "Male", "Female", "Female")
Education_level <- c("Secondary incomplete", "Secondary incomplete", "Primary incomplete", "Secondary complete", "Secondary complete", "Secondary complete", "Primary complete", "Post-secondary", "Secondary incomplete", "Secondary incomplete")
Labor_status <- c("Employed", "Employed", "Non-LF", "Employed", "Unemployed", "Employed", "Non-LF", "Unemployed", "Non-LF", "Non-LF")
Health <- c("yes", "yes", "yes", "yes", "yes", "no", "no", "yes", "no", "yes")
Weight <- c(180, 180, 215, 76, 186, 76, 180, 215, 186, 76)
# fk <- c(2, 2, 1, 2, 1, 2, 1, 1, 2, 2)
# Fk <- c(360, 360, 215, 152, 186, 152, 180, 215, 262, 262)
# risk <- c(0.0054, 0.0054, 0.0251, 0.0126, 0.0282, 0.0126, 0.0290, 0.0251, 0.0074, 0.0074)
dados <- data.frame(No, Residence, Gender, Education_level, Labor_status, Health, Weight)
selectedKeyVars = c('Residence', 'Gender', 'Education_level', 'Labor_status')
selectedWeightVar = c('Weight')
selectedSensibleVar = c('Health')
sdcInitial <- createSdcObj(dat  = dados,
keyVars     = selectedKeyVars,
# ghostVars   = selectedGhostVars,
# numVar      = selectedNumVar,
weightVar   = selectedWeightVar,
# pramVars    = selectedPramVars,
# hhId        = selectedHouseholdID,
# strataVar   = selectedStrataVar,
sensibleVar = selectedSensibleVar,
alpha = 0)
sdcInitial@risk
risk <- sdcInitial@risk$individual
dados2 <- cbind(dados, risk)
dados2$kAnon <- dados2$fk + 1
print(sdcInitial, 'kAnon')
sum(sdcInitial@risk$individual[,2] < 5)
sdcInitial <- ldiversity(obj = sdcInitial, ldiv_index = c("Health"))
sdcInitial@risk$ldiversity
sdcInitial <- ldiversity(obj = sdcInitial, ldiv_index = c("Health"), l_recurs_c = 2, missing = NA)
# Output for l-diversity
sdcInitial@risk$ldiversity
View(dados3)
library(sdcMicro)
No <- c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)
Residence <- c("Urban", "Urban", "Urban", "Urban", "Rural", "Urban", "Urban", "Urban", "Urban", "Urban")
Gender <- c("Female", "Female", "Female", "Male", "Female", "Male", "Female", "Male", "Female", "Female")
Education_level <- c("Secondary incomplete", "Secondary incomplete", "Primary incomplete", "Secondary complete", "Secondary complete", "Secondary complete", "Primary complete", "Post-secondary", "Secondary incomplete", "Secondary incomplete")
Labor_status <- c("Employed", "Employed", "Non-LF", "Employed", "Unemployed", "Employed", "Non-LF", "Unemployed", "Non-LF", "Non-LF")
Health <- c("yes", "yes", "yes", "yes", "yes", "no", "no", "yes", "no", "yes")
Weight <- c(180, 180, 215, 76, 186, 76, 180, 215, 186, 76)
# fk <- c(2, 2, 1, 2, 1, 2, 1, 1, 2, 2)
# Fk <- c(360, 360, 215, 152, 186, 152, 180, 215, 262, 262)
# risk <- c(0.0054, 0.0054, 0.0251, 0.0126, 0.0282, 0.0126, 0.0290, 0.0251, 0.0074, 0.0074)
dados <- data.frame(No, Residence, Gender, Education_level, Labor_status, Health, Weight)
selectedKeyVars = c("Residence", "Gender", "Education_level", "Labor_status")
selectedWeightVar = c("Weight")
selectedSensibleVar = c("Health")
sdcInitial <- createSdcObj(dat  = dados,
keyVars     = selectedKeyVars,
# ghostVars   = selectedGhostVars,
# numVar      = selectedNumVar,
weightVar   = selectedWeightVar,
# pramVars    = selectedPramVars,
# hhId        = selectedHouseholdID,
# strataVar   = selectedStrataVar,
sensibleVar = selectedSensibleVar,
alpha = 0)
sdcInitial@risk
risk <- sdcInitial@risk$individual
dados2 <- cbind(dados, risk)
dados2$kAnon <- dados2$fk + 1
print(sdcInitial, 'kAnon')
sum(sdcInitial@risk$individual[,2] < 5)
sdcInitial <- ldiversity(obj = sdcInitial, ldiv_index = c("Health"))
sdcInitial@risk$ldiversity
View(dados3)
View(dados3)
View(sdcInitial)
ldiversity
View(sdcInitial)
View(sdcInitial)
sdcInitial@risk$ldiversity
sdcInitial@risk$ldiversity[,'Health_Distinct_Ldiversity']
library(sdcMicro)
No <- c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)
Residence <- c("Urban", "Urban", "Urban", "Urban", "Rural", "Urban", "Urban", "Urban", "Urban", "Urban")
Gender <- c("Female", "Female", "Female", "Male", "Female", "Male", "Female", "Male", "Female", "Female")
Education_level <- c("Secondary incomplete", "Secondary incomplete", "Primary incomplete", "Secondary complete", "Secondary complete", "Secondary complete", "Primary complete", "Post-secondary", "Secondary incomplete", "Secondary incomplete")
Labor_status <- c("Employed", "Employed", "Non-LF", "Employed", "Unemployed", "Employed", "Non-LF", "Unemployed", "Non-LF", "Non-LF")
Health <- c("yes", "yes", "yes", "yes", "yes", "no", "no", "yes", "no", "yes")
Weight <- c(180, 180, 215, 76, 186, 76, 180, 215, 186, 76)
# fk <- c(2, 2, 1, 2, 1, 2, 1, 1, 2, 2)
# Fk <- c(360, 360, 215, 152, 186, 152, 180, 215, 262, 262)
# risk <- c(0.0054, 0.0054, 0.0251, 0.0126, 0.0282, 0.0126, 0.0290, 0.0251, 0.0074, 0.0074)
dados <- data.frame(No, Residence, Gender, Education_level, Labor_status, Health, Weight)
selectedKeyVars = c("Residence", "Gender", "Education_level", "Labor_status")
selectedWeightVar = c("Weight")
selectedSensibleVar = c("Health")
sdcInitial <- createSdcObj(dat  = dados,
keyVars     = selectedKeyVars,
# ghostVars   = selectedGhostVars,
# numVar      = selectedNumVar,
weightVar   = selectedWeightVar,
# pramVars    = selectedPramVars,
# hhId        = selectedHouseholdID,
# strataVar   = selectedStrataVar,
sensibleVar = selectedSensibleVar,
alpha = 0)
sdcInitial@risk
risk <- sdcInitial@risk$individual
dados2 <- cbind(dados, risk)
dados2$kAnon <- dados2$fk + 1
print(sdcInitial, 'kAnon')
sum(sdcInitial@risk$individual[,2] < 5)
sdcInitial <- ldiversity(obj = sdcInitial, ldiv_index = c("Health"))
sdcInitial@risk$ldiversity
sdcInitial@risk$ldiversity[,'Health_Distinct_Ldiversity']
ldive <- sdcInitial@risk$ldiversity[,'Health_Distinct_Ldiversity']
dados3 <- cbind(dados2, ldive)
View(sdcInitial)
View(dados3)
sdcInitial <- ldiversity(obj = sdcInitial, ldiv_index = c("Health"), l_recurs_c = 1)
sdcInitial@risk$ldiversity
sdcInitial <- ldiversity(obj = sdcInitial, ldiv_index = c("Health"), missing = -999)
sdcInitial <- ldiversity(obj = sdcInitial, ldiv_index = c("Health"), missing = NA)
library(sdcMicro)
No <- c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)
Residence <- c("Urban", "Urban", "Urban", "Urban", "Rural", "Urban", "Urban", "Urban", "Urban", "Urban")
Gender <- c("Female", "Female", "Female", "Male", "Female", "Male", "Female", "Male", "Female", "Female")
Education_level <- c("Secondary incomplete", "Secondary incomplete", "Primary incomplete", "Secondary complete", "Secondary complete", "Secondary complete", "Primary complete", "Post-secondary", "Secondary incomplete", "Secondary incomplete")
Labor_status <- c("Employed", "Employed", "Non-LF", "Employed", "Unemployed", "Employed", "Non-LF", "Unemployed", "Non-LF", "Non-LF")
Health <- c("yes", "yes", "yes", "yes", "yes", "no", "no", "yes", "no", "yes")
Weight <- c(180, 180, 215, 76, 186, 76, 180, 215, 186, 76)
# fk <- c(2, 2, 1, 2, 1, 2, 1, 1, 2, 2)
# Fk <- c(360, 360, 215, 152, 186, 152, 180, 215, 262, 262)
# risk <- c(0.0054, 0.0054, 0.0251, 0.0126, 0.0282, 0.0126, 0.0290, 0.0251, 0.0074, 0.0074)
dados <- data.frame(No, Residence, Gender, Education_level, Labor_status, Health, Weight)
selectedSensibleVar = c("Health")
sdcInitial <- createSdcObj(dat  = dados,
keyVars = c("Residence", "Gender", "Education_level", "Labor_status"),
weightVar = c("Weight"),
sensibleVar = c("Health"),
alpha = 0)
sdcInitial@risk
risk <- sdcInitial@risk$individual
dados2 <- cbind(dados, risk)
dados2$kAnon <- dados2$fk + 1
print(sdcInitial, 'kAnon')
sum(sdcInitial@risk$individual[,2] < 5)
sdcInitial <- ldiversity(obj = sdcInitial, ldiv_index = c("Health"), missing = NA)
sdcInitial@risk$ldiversity
sdcInitial@risk$ldiversity[,'Health_Distinct_Ldiversity']
ldive <- sdcInitial@risk$ldiversity[,'Health_Distinct_Ldiversity']
dados3 <- cbind(dados2, ldive)
sdcInitial <- createSdcObj(dat  = dados,
keyVars = c("Labor_status", "Residence", "Gender", "Education_level"),
weightVar = c("Weight"),
sensibleVar = c("Health"),
alpha = 0)
sdcInitial@risk
risk <- sdcInitial@risk$individual
dados2 <- cbind(dados, risk)
dados2$kAnon <- dados2$fk + 1
print(sdcInitial, 'kAnon')
sum(sdcInitial@risk$individual[,2] < 5)
sdcInitial <- ldiversity(obj = sdcInitial, ldiv_index = c("Health"), missing = NA)
sdcInitial@risk$ldiversity
sdcInitial@risk$ldiversity[,'Health_Distinct_Ldiversity']
ldive <- sdcInitial@risk$ldiversity[,'Health_Distinct_Ldiversity']
library(sdcMicro)
No <- c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)
Residence <- c("Urban", "Urban", "Urban", "Urban", "Rural", "Urban", "Urban", "Urban", "Urban", "Urban")
Gender <- c("Female", "Female", "Female", "Male", "Female", "Male", "Female", "Male", "Female", "Female")
Education_level <- c("Secondary incomplete", "Secondary incomplete", "Primary incomplete", "Secondary complete", "Secondary complete", "Secondary complete", "Primary complete", "Post-secondary", "Secondary incomplete", "Secondary incomplete")
Labor_status <- c("Employed", "Employed", "Non-LF", "Employed", "Unemployed", "Employed", "Non-LF", "Unemployed", "Non-LF", "Non-LF")
Health <- c("yes", "yes", "yes", "yes", "yes", "no", "no", "yes", "no", "yes")
Weight <- c(180, 180, 215, 76, 186, 76, 180, 215, 186, 76)
# fk <- c(2, 2, 1, 2, 1, 2, 1, 1, 2, 2)
# Fk <- c(360, 360, 215, 152, 186, 152, 180, 215, 262, 262)
# risk <- c(0.0054, 0.0054, 0.0251, 0.0126, 0.0282, 0.0126, 0.0290, 0.0251, 0.0074, 0.0074)
dados <- data.frame(No, Residence, Gender, Education_level, Labor_status, Health, Weight)
selectedSensibleVar = c("Health")
sdcInitial <- createSdcObj(dat  = dados,
keyVars = c("Residence", "Gender", "Education_level", "Labor_status"),
weightVar = c("Weight"),
sensibleVar = c("Health"),
alpha = 0)
sdcInitial@risk
risk <- sdcInitial@risk$individual
dados2 <- cbind(dados, risk)
dados2$kAnon <- dados2$fk + 1
print(sdcInitial, 'kAnon')
sum(sdcInitial@risk$individual[,2] < 5)
sdcInitial <- ldiversity(obj = sdcInitial, ldiv_index = c("Health"))
sdcInitial@risk$ldiversity
sdcInitial@risk$ldiversity[,'Health_Distinct_Ldiversity']
ldive <- sdcInitial@risk$ldiversity[,'Health_Distinct_Ldiversity']
dados3 <- cbind(dados2, ldive)
View(sdcInitial)
View(dados)
library(sdcMicro)
No <- c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)
Residence <- c("Urban", "Urban", "Urban", "Urban", "Rural", "Urban", "Urban", "Urban", "Urban", "Urban")
Gender <- c("Female", "Female", "Female", "Male", "Female", "Male", "Female", "Male", "Female", "Female")
Education_level <- c("Secondary incomplete", "Secondary incomplete", "Primary incomplete", "Secondary complete", "Secondary complete", "Secondary complete", "Primary complete", "Post-secondary", "Secondary incomplete", "Secondary incomplete")
Labor_status <- c("Employed", "Employed", "Non-LF", "Employed", "Unemployed", "Employed", "Non-LF", "Unemployed", "Non-LF", "Non-LF")
Health <- c("yes", "yes", "yes", "yes", "yes", "no", "no", "yes", "no", "yes")
Weight <- c(180, 180, 215, 76, 186, 76, 180, 215, 186, 76)
# fk <- c(2, 2, 1, 2, 1, 2, 1, 1, 2, 2)
# Fk <- c(360, 360, 215, 152, 186, 152, 180, 215, 262, 262)
# risk <- c(0.0054, 0.0054, 0.0251, 0.0126, 0.0282, 0.0126, 0.0290, 0.0251, 0.0074, 0.0074)
dados <- data.frame(No, Residence, Gender, Education_level, Labor_status, Health, Weight)
sdcInitial <- createSdcObj(dat  = dados,
keyVars = c("Residence", "Gender", "Education_level", "Labor_status"),
weightVar = c("Weight"),
sensibleVar = c("Health"),
alpha = 0)
sdcInitial@risk
risk <- sdcInitial@risk$individual
dados2 <- cbind(dados, risk)
dados2$kAnon <- dados2$fk + 1
print(sdcInitial, 'kAnon')
sum(sdcInitial@risk$individual[,2] < 5)
sdcInitial <- ldiversity(obj = sdcInitial, ldiv_index = c("Health"))
sdcInitial@risk$ldiversity
nome <- c("Mayra", "Fabio")
idade <- c(31, 36)
dados <- data.frame(nome, idade)
View(dados)
library(xlsx)
readxl::read_xlsx("C:/Users/mpizzott/Desktop/Pasta1.xlsx")
dados <- readxl::read_xlsx("C:/Users/mpizzott/Desktop/Pasta1.xlsx")
View(dados)
str(dados)
dados <- readxl::read_xlsx("C:/Users/mpizzott/Desktop/Pasta1.xlsx")
str(dados)
View(dados)
head(dados[,5])
dados[,5]
dados[5,]
rm(list = ls()) # Remove objetos da memória (Global Environment)
cat("\014") # Limpa console R
options(scipen=999) # Desabilita resultados em notação científica
library(tidyverse)
library(haven)
library(labelled)
dados <- read_sav("Z:/CETIC.BR (repositório)/Pesquisas/TIC EMPRESAS/2019/Processamento/Microdados/Final/TIC_EMP_PONDERADA_FINAL.sav")
# ******************************************************************************
# *** Pesquisa TIC KIDS ONLNE 2023
# *** Preparação da base de microdados
# *** Programador(a): Mayra Pizzott
# *** Última atualização: 23/10/2023
# ******************************************************************************
rm(list = ls()) # Remove objetos da memória (Global Environment)
cat("\014") # Limpa console R
# Carrega (e instala, se necessário) pacotes requeridos
if (!require("install.load")) install.packages("install.load")
suppressMessages(install.load::install_load("tidyverse", "survey", "haven"))
# Define a pasta de trabalho (diretório onde se encontra a base final)
setwd("Z:/CETIC.BR (repositório)/Pesquisas/TIC KIDS ONLINE/2023/Processamento/Tabelas")
# Leitura dos dados de kids
dados_kids <- read_sav("./Crianças e adolescentes/tic_kids_online_brasil_2023_criancas_dados.sav")
# Verifica variáveis do plano amostral
table(dados_kids$ESTRATO, exclude = NULL)
length(unique(dados_kids$ESTRATO))
table(dados_kids$UPA, exclude = NULL)
length(unique(dados_kids$UPA))
sum(dados_kids$PESO)
summary(dados_kids$PESO)
# Recodifica a variável ESTRATO
ESTRATO2 <- dados_kids %>%
group_by(ESTRATO) %>%
summarise(n = n()) %>%
mutate(ESTRATO1 = seq(1,length(ESTRATO)))
dados_kids <- left_join(dados_kids, ESTRATO2, by = "ESTRATO")
rm(ESTRATO2)
table(dados_kids$ESTRATO1)
# Recodifica a variável UPA
UPA2 <- dados_kids %>%
group_by(UPA) %>%
summarise(n = n()) %>%
mutate(UPA1 = seq(1,length(UPA)))
dados_kids <- left_join(dados_kids, UPA2, by = "UPA")
rm(UPA2)
table(dados_kids$UPA1)
# Remove variáveis
dados_kids <- dados_kids %>% select(-c(RENDA_FAMILIAR, COD_REGIAO, A4,
contains("AJUDA"), contains("DESC"),
ESTRATO, UPA, O2, starts_with("AV"),
M2, M8, D1, D2, D3_A, D3_B, D3_C, D3_D,
D3_E, D3_F, D3_G, D3_H, D3_I, D3_OUTRO,
D4, CLASSE_CB2015, RESP_ESCOLARIDADE,
# RESP_SEXO,  RESP_PEA,
RESP_IDADE, RACA_RESP_KIDS, IDADE_KIDS,
ESC1, RELIGIAO_KIDS, n.x, n.y,
T5_NS, T5_NR, T5_NA, T7_NS, T7_NR, T7_NA,
T9_NS, T9_NR, A_TOTAL))
# Renomeia variáveis
dados_kids <- dados_kids %>% rename(ESTRATO = ESTRATO1,
UPA = UPA1)
#Criando o desenho amostral
design_kids <- svydesign(ids =~ UPA,
strata =~ ESTRATO,
weights =~ PESO,
data = dados_kids)
# # Converte o tipo de todas as variáveis que possuem label para fator
# design_kids$variables <- as_factor(design_kids$variables,
#                                       only_labelled = TRUE,
#                                       levels = "default",
#                                       ordered = FALSE)
#desenho amostral considerando 200 réplicas
boot_design_kids <- as.svrepdesign(design_kids, type = "bootstrap",
replicates = 200, compress = FALSE)
rm(design_kids)
escala_kids <- boot_design_kids$scale
escala_kids
write.csv2(escala_kids, file = "Z:/CETIC.BR (repositório)/Administração Cetic/3. Termo Acesso Base Microdados/Microdados/TIC_KIDS para download/2023/escala_kids23.csv")
boot_design_kids$repweights
reppeso <- as.data.frame(boot_design_kids$repweights)
names(reppeso) <- sub("V","rep",names(reppeso))
dados_kids <- boot_design_kids$variables
dados_kids$PESO<-NULL
PESO <- as.data.frame(boot_design_kids$pweights)
names(PESO) <- "PESO"
dados_kids <- cbind(dados_kids, PESO, reppeso)
rm(PESO, reppeso)
sum(boot_design_kids$pweights)
sum(dados_kids$PESO)
design_kids <- svrepdesign(weights=~PESO,
repweights="rep[1-200]+",
type="bootstrap",
scale = 0.00575932116864683,
data=dados_kids,
combined.weights=FALSE)
rm(boot_design_kids)
# Exclui as variaveis ESTRATO e UPA
dados_kids <- dados_kids %>% select(-c(ESTRATO, UPA))
design_kids$variables <- subset(design_kids$variables, select = -c(ESTRATO, UPA))
#teste para conferir os valores (comparar com tabelas)
# options(survey.lonely.psu="adjust")
A1C_crianças <- svyby(~as.factor(M3), ~AREA, design = design_kids, svymean)
design_kidsM3 <- subset(design_kids, M3 == 1) # Total de usuários de Internet de 9 a 17 anos
A1E_crianças <- svyby(~as.factor(M1_DISPOSITIVOS), ~FAIXA_ETARIA, design = design_kidsM3, svymean)
design_kidsM3$variables$E3 <- as.factor(design_kidsM3$variables$E3)
C1_pais <- svyby(~as.factor(E3), ~COD_REGIAO_2, design = design_kidsM3, svymean)
design_kidsM3$variables$L4 <- as.factor(design_kidsM3$variables$L4)
B4A_pais <- svyby(~as.factor(L4), ~A4_AGREG, design = design_kidsM3, svymean)
# D1_pais <- svyby(~as.factor(F1), ~A4_AGREG, design = design_kidsM3, svymean)
design_kidsM3$variables$D5 <- as.factor(design_kidsM3$variables$D5)
A3_pais <- svyby(~as.factor(D5), ~CLASSE_2015_REC, design = design_kidsM3, svymean)
# Define diretório (pasta onde salvar os microdados)
setwd("Z:/CETIC.BR (repositório)/Administração Cetic/3. Termo Acesso Base Microdados/Microdados/TIC_KIDS para download/2023/1.base_de_microdados")
# Salva o objeto (svy)
save(design_kids, file = "tic_kids_online_brasil_2023_base_de_microdados_v1.0.RData")
# Salva em csv
write.csv2(dados_kids, file = "tic_kids_online_brasil_2023_base_de_microdados_v1.0.csv", row.names = FALSE)
# Salva em sav
write_sav(dados_kids, path = "tic_kids_online_brasil_2023_base_de_microdados_v1.0.sav")
## Teste para carregar os arquivos
# load("tic_kids_online_brasil_2023_base_de_microdados_v1.0.RData")
# ******************************************************************************
# *** Pesquisa TIC KIDS ONLNE 2023
# *** Preparação da base de microdados
# *** Programador(a): Mayra Pizzott
# *** Última atualização: 23/10/2023
# ******************************************************************************
rm(list = ls()) # Remove objetos da memória (Global Environment)
cat("\014") # Limpa console R
# Carrega (e instala, se necessário) pacotes requeridos
if (!require("install.load")) install.packages("install.load")
suppressMessages(install.load::install_load("tidyverse", "survey", "haven"))
# Define a pasta de trabalho (diretório onde se encontra a base final)
setwd("Z:/CETIC.BR (repositório)/Pesquisas/TIC KIDS ONLINE/2023/Processamento/Tabelas")
# Leitura dos dados de kids
dados_kids <- read_sav("./Crianças e adolescentes/tic_kids_online_brasil_2023_criancas_dados.sav")
# Verifica variáveis do plano amostral
table(dados_kids$ESTRATO, exclude = NULL)
length(unique(dados_kids$ESTRATO))
table(dados_kids$UPA, exclude = NULL)
length(unique(dados_kids$UPA))
sum(dados_kids$PESO)
summary(dados_kids$PESO)
# Recodifica a variável ESTRATO
ESTRATO2 <- dados_kids %>%
group_by(ESTRATO) %>%
summarise(n = n()) %>%
mutate(ESTRATO1 = seq(1,length(ESTRATO)))
dados_kids <- left_join(dados_kids, ESTRATO2, by = "ESTRATO")
rm(ESTRATO2)
table(dados_kids$ESTRATO1)
# Recodifica a variável UPA
UPA2 <- dados_kids %>%
group_by(UPA) %>%
summarise(n = n()) %>%
mutate(UPA1 = seq(1,length(UPA)))
dados_kids <- left_join(dados_kids, UPA2, by = "UPA")
rm(UPA2)
table(dados_kids$UPA1)
# Remove variáveis
dados_kids <- dados_kids %>% select(-c(RENDA_FAMILIAR, COD_REGIAO, A4,
contains("AJUDA"), contains("DESC"),
ESTRATO, UPA, O2, starts_with("AV"),
M2, M8, D1, D2, D3_A, D3_B, D3_C, D3_D,
D3_E, D3_F, D3_G, D3_H, D3_I, D3_OUTRO,
D4, CLASSE_CB2015, RESP_ESCOLARIDADE,
# RESP_SEXO,  RESP_PEA,
RESP_IDADE, RACA_RESP_KIDS, IDADE_KIDS,
ESC1, RELIGIAO_KIDS, n.x, n.y,
T5_NS, T5_NR, T5_NA, T7_NS, T7_NR, T7_NA,
T9_NS, T9_NR, A_TOTAL))
# Renomeia variáveis
dados_kids <- dados_kids %>% rename(ESTRATO = ESTRATO1,
UPA = UPA1)
#Criando o desenho amostral
design_kids <- svydesign(ids =~ UPA,
strata =~ ESTRATO,
weights =~ PESO,
data = dados_kids)
# # Converte o tipo de todas as variáveis que possuem label para fator
# design_kids$variables <- as_factor(design_kids$variables,
#                                       only_labelled = TRUE,
#                                       levels = "default",
#                                       ordered = FALSE)
#desenho amostral considerando 200 réplicas
boot_design_kids <- as.svrepdesign(design_kids, type = "bootstrap",
replicates = 200, compress = FALSE)
rm(design_kids)
escala_kids <- boot_design_kids$scale
escala_kids
write.csv2(escala_kids, file = "Z:/CETIC.BR (repositório)/Administração Cetic/3. Termo Acesso Base Microdados/Microdados/TIC_KIDS para download/2023/escala_kids23.csv")
boot_design_kids$repweights
reppeso <- as.data.frame(boot_design_kids$repweights)
names(reppeso) <- sub("V","rep",names(reppeso))
dados_kids <- boot_design_kids$variables
dados_kids$PESO<-NULL
PESO <- as.data.frame(boot_design_kids$pweights)
names(PESO) <- "PESO"
dados_kids <- cbind(dados_kids, PESO, reppeso)
rm(PESO, reppeso)
sum(boot_design_kids$pweights)
sum(dados_kids$PESO)
design_kids <- svrepdesign(weights=~PESO,
repweights="rep[1-200]+",
type="bootstrap",
scale = 0.00575932116864683,
data=dados_kids,
combined.weights=FALSE)
rm(boot_design_kids)
# Exclui as variaveis ESTRATO e UPA
dados_kids <- dados_kids %>% select(-c(ESTRATO, UPA))
design_kids$variables <- subset(design_kids$variables, select = -c(ESTRATO, UPA))
#teste para conferir os valores (comparar com tabelas)
# options(survey.lonely.psu="adjust")
A1C_crianças <- svyby(~as.factor(M3), ~AREA, design = design_kids, svymean)
design_kidsM3 <- subset(design_kids, M3 == 1) # Total de usuários de Internet de 9 a 17 anos
A1E_crianças <- svyby(~as.factor(M1_DISPOSITIVOS), ~FAIXA_ETARIA, design = design_kidsM3, svymean)
design_kidsM3$variables$E3 <- as.factor(design_kidsM3$variables$E3)
C1_pais <- svyby(~as.factor(E3), ~COD_REGIAO_2, design = design_kidsM3, svymean)
design_kidsM3$variables$L4 <- as.factor(design_kidsM3$variables$L4)
B4A_pais <- svyby(~as.factor(L4), ~A4_AGREG, design = design_kidsM3, svymean)
# D1_pais <- svyby(~as.factor(F1), ~A4_AGREG, design = design_kidsM3, svymean)
design_kidsM3$variables$D5 <- as.factor(design_kidsM3$variables$D5)
A3_pais <- svyby(~as.factor(D5), ~CLASSE_2015_REC, design = design_kidsM3, svymean)
# Define diretório (pasta onde salvar os microdados)
setwd("Z:/CETIC.BR (repositório)/Pesquisas/TIC KIDS ONLINE/2023/Site/1. Base de microdados")
# Salva o objeto (svy)
save(design_kids, file = "tic_kids_online_brasil_2023_base_de_microdados_v1.0.RData")
# Salva em csv
write.csv2(dados_kids, file = "tic_kids_online_brasil_2023_base_de_microdados_v1.0.csv", row.names = FALSE)
# Salva em sav
write_sav(dados_kids, path = "tic_kids_online_brasil_2023_base_de_microdados_v1.0.sav")
## Teste para carregar os arquivos
# load("tic_kids_online_brasil_2023_base_de_microdados_v1.0.RData")
