Calculate the total and its variation using survey methods

Source: R/survey_statistics.r

Calculate totals from complex survey data. A wrapper around svytotal. survey_total should always be called from summarise.

survey_total(
  x,
  na.rm = FALSE,
  vartype = c("se", "ci", "var", "cv"),
  level = 0.95,
  deff = FALSE,
  df = NULL,
  ...
)

Arguments

x

A variable or expression, or empty
na.rm

A logical value to indicate whether missing values should be dropped
vartype

Report variability as one or more of: standard error ("se", default), confidence interval ("ci"), variance ("var") or coefficient of variation ("cv").
level

A single number or vector of numbers indicating the confidence level
deff

A logical value to indicate whether the design effect should be returned.
df

(For vartype = "ci" only) A numeric value indicating the degrees of freedom for t-distribution. The default (NULL) uses degf, but Inf is the usual survey package's default.
...

Ignored

Examples

library(survey)
data(api)

dstrata <- apistrat %>%
  as_survey_design(strata = stype, weights = pw)

dstrata %>%
  summarise(enroll_tot = survey_total(enroll),
            tot_meals = survey_total(enroll * meals / 100, vartype = c("ci", "cv")))

#> # A tibble: 1 × 6
#>   enroll_tot enroll_tot_se tot_meals tot_meals_low tot_meals_upp tot_meals_cv
#>        <dbl>         <dbl>     <dbl>         <dbl>         <dbl>        <dbl>
#> 1   3687178.       117319.  1753775.      1528167.      1979384.       0.0652

dstrata %>%
  group_by(awards) %>%
  summarise(api00 = survey_total(enroll))

#> # A tibble: 2 × 3
#>   awards    api00 api00_se
#>   <fct>     <dbl>    <dbl>
#> 1 No     1627217.  147847.
#> 2 Yes    2059960.  143734.

# Leave x empty to calculate the total in each group
dstrata %>%
  group_by(awards) %>%
  summarise(pct = survey_total())

#> # A tibble: 2 × 3
#>   awards   pct pct_se
#>   <fct>  <dbl>  <dbl>
#> 1 No     2236.   216.
#> 2 Yes    3958.   216.

# level takes a vector for multiple levels of confidence intervals
dstrata %>%
  summarise(enroll = survey_total(enroll, vartype = "ci", level = c(0.95, 0.65)))

#> # A tibble: 1 × 5
#>     enroll enroll_low95 enroll_upp95 enroll_low65 enroll_upp65
#>      <dbl>        <dbl>        <dbl>        <dbl>        <dbl>
#> 1 3687178.     3455815.     3918540.     3577271.     3797084.

# Note that the default degrees of freedom in srvyr is different from
# survey, so your confidence intervals might not exactly match. To
# replicate survey's behavior, use df = Inf
dstrata %>%
  summarise(srvyr_default = survey_total(api99, vartype = "ci"),
            survey_defualt = survey_total(api99, vartype = "ci", df = Inf))

#> # A tibble: 1 × 6
#>   srvyr_default srvyr_default_low srvyr_default_upp survey_def…¹ surve…² surve…³
#>           <dbl>             <dbl>             <dbl>        <dbl>   <dbl>   <dbl>
#> 1      3898472.          3775136.          4021807.     3898472.  3.78e6  4.02e6
#> # … with abbreviated variable names ¹​survey_defualt, ²​survey_defualt_low,
#> #   ³​survey_defualt_upp

comparison <- survey::svytotal(~api99, dstrata)
confint(comparison) # survey's default

#>         2.5 %  97.5 %
#> api99 3775894 4021049
confint(comparison, df = survey::degf(dstrata)) # srvyr's default

#>         2.5 %  97.5 %
#> api99 3775136 4021807