Reduce the dimensionality of the table

collapse_table(
  poptable,
  area_var,
  X_vars,
  count_var,
  report = "counts",
  new_name = "n_aggregate",
  warnings = FALSE
)

Arguments

poptable: The population table, collapsed in terms of counts. Must contain all variables in the RHS of formula, as well as the variables specified in area_var and count_var below.
area_var: A character vector of the area of interest.
X_vars: A character vector of the variables to keep. By design, this should be fewer variables than what is available in poptable.
count_var: A character variable that specifies which variable in poptable indicates the count
report: Should the output be in simple counts (the default, "counts") or the proportion that count represents in the area ("proportions")?
new_name: What should the new count (or proportion) variable be called?
warnings: Show some warnings about zero cells in the original data? Defaults to FALSE

Value

A dataframe of counts or proportions. By design, it will include the variables area_var, X_vars, and whatever is specified in new_name.

Examples


 # If you want to estimate education by female and age
 collapse_table(acs_race_NY, area_var = "cd", X_vars = c("female", "age"),
                count_var = "count")
#> # A tibble: 270 × 4
#>    cd    female age               n_aggregate
#>    <chr>  <int> <fct>                   <dbl>
#>  1 NY-01      0 18 to 24 years          34123
#>  2 NY-01      0 25 to 34 years          45361
#>  3 NY-01      0 35 to 44 years          41146
#>  4 NY-01      0 45 to 64 years         104998
#>  5 NY-01      0 65 years and over       57557
#>  6 NY-01      1 18 to 24 years          32579
#>  7 NY-01      1 25 to 34 years          42309
#>  8 NY-01      1 35 to 44 years          42232
#>  9 NY-01      1 45 to 64 years         104236
#> 10 NY-01      1 65 years and over       71758
#> # … with 260 more rows

 # Report proportions
 collapse_table(acs_race_NY, area_var = "cd", X_vars = c("female", "age"),
                count_var = "count",
                report = "proportions", new_name = "prop_in_cd")
#> Warning: You asked for proporitons but the value of `new_name` looks more appropriate for a count.
#> # A tibble: 270 × 4
#>    cd    female age               prop_in_cd
#>    <chr>  <int> <fct>                  <dbl>
#>  1 NY-01      0 18 to 24 years        0.0592
#>  2 NY-01      0 25 to 34 years        0.0787
#>  3 NY-01      0 35 to 44 years        0.0714
#>  4 NY-01      0 45 to 64 years        0.182 
#>  5 NY-01      0 65 years and over     0.0999
#>  6 NY-01      1 18 to 24 years        0.0565
#>  7 NY-01      1 25 to 34 years        0.0734
#>  8 NY-01      1 35 to 44 years        0.0733
#>  9 NY-01      1 45 to 64 years        0.181 
#> 10 NY-01      1 65 years and over     0.125 
#> # … with 260 more rows