1960 census

R/read_households.R

@@ -12,6 +12,9 @@
 #' @template cache
 #'
 #' @return An arrow `Dataset` or a `"data.frame"` object.
+#'
+#' @template 1960_census_section
+#'
 #' @export
 #' @family Microdata
 #' @examplesIf identical(tolower(Sys.getenv("NOT_CRAN")), "true")
@@ -34,7 +37,7 @@ read_households <- function(year = 2010,
   checkmate::assert_string(add_labels, pattern = 'pt', null.ok = TRUE)
 
   # data available for the years:
-  years <- c(1970, 1980, 1991, 2000, 2010)
+  years <- c(1960, 1970, 1980, 1991, 2000, 2010)
   if (isFALSE(year %in% years)) { stop(paste0("Error: Data currently only available for the years ",
                                               paste(years, collapse = " ")))}
 
@@ -67,6 +70,11 @@ read_households <- function(year = 2010,
                                 lang = add_labels)
   }
 
+  # 1960 warning
+  if(year==1960){
+    warning("This version of the 1960 microdata was compiled by {censobr} from two different releases elaborated by IBGE. The data was processed to ensure consistency and new variables added. See the documentation")
+    }
+
   ### output format
   if (isTRUE(as_data_frame)) { return( dplyr::collect(df) )
   } else {

R/read_population.R

@@ -12,6 +12,9 @@
 #' @template cache
 #'
 #' @return An arrow `Dataset` or a `"data.frame"` object.
+#'
+#' @template 1960_census_section
+#'
 #' @export
 #' @family Microdata
 #' @examplesIf identical(tolower(Sys.getenv("NOT_CRAN")), "true")
@@ -35,7 +38,7 @@ read_population <- function(year = 2010,
   checkmate::assert_string(add_labels, pattern = 'pt', null.ok = TRUE)
 
   # data available for the years:
-  years <- c(1970, 1980, 1991, 2000, 2010)
+  years <- c(1960, 1970, 1980, 1991, 2000, 2010)
   if (isFALSE(year %in% years)) { stop(paste0("Error: Data currently only available for the years ",
                                              paste(years, collapse = " ")))}
 
@@ -76,6 +79,11 @@ read_population <- function(year = 2010,
                                 lang = add_labels)
   }
 
+  # 1960 warning
+  if(year==1960){
+    warning("This version of the 1960 microdata was compiled by {censobr} from two different releases elaborated by IBGE. The data was processed to ensure consistency and new variables added. See the documentation")
+  }
+
   ### output format
   if (isTRUE(as_data_frame)) { return( dplyr::collect(df) )
   } else {

cran-comments.md

@@ -1,7 +1,7 @@
 ## R CMD check results
 
-── R CMD check results ────────────────────────────── censobr 0.3.9999999 ────
-Duration: 5m 52.9s
+── R CMD check results ──────────────────────────────── censobr 0.3.29999 ────
+Duration: 10m 48.6s
 
 0 errors ✔ | 0 warnings ✔ | 0 notes ✔
 

man/roxygen/templates/1960_census_section.R

@@ -0,0 +1,26 @@
+#' @section 1960 Census:
+#'
+#'The 1960 microdata version available in **{censobr}** is a combination of two
+#'versions of the Demographic Census sample. The 25% sample data from the 1960
+#'Census was never fully processed by IBGE - several states did not have their
+#'questionnaires digitized. Currently, this dataset only has data from 16 states
+#'of the Federation (and from a contested border region between Minas Gerais and
+#'Espirito Santo called Serra dos Aimores). Information is missing for the states
+#'of the former Northern Region, Maranhão, Piaui, Guanabara, Santa Catarina, and
+#'Espírito Santo. In 1965, IBGE decided to draw a probabilistic sub-sample of
+#'approximately 1.27% of the population, including all units of the federation.
+#'With this data, IBGE produced several official reports at the time. The data
+#'from **{censobr}** is the combination of these two datasets.
+#'
+#'We processed and ensured the consistency of the 1.27% sample data, which was
+#'partially corrupted. We also created a sample weight variable to correct for
+#'disproportionalities and to expand te sample to the total population. For the
+#'data from the 25% sample, the weights expand to the municipal totals.
+#'Meanwhile, for the data from the 1.27% sample, the weights expand to the state
+#'totals. Additionally, we constructed a few variables that allow for the
+#'approximate incorporation of the complex sample design, enabling the proper
+#'calculation of standard errors and confidence intervals.
+#'
+#'You can read more about the 1960 Census and find a thogorugh documentation of
+#'how this dataset was processed on this link \url{https://github.com/antrologos/ConsistenciaCenso1960Br}.
+