Skip to contents

Proportion Difference

Source: R/prop_diff.R
prop_diff.Rd

[Stable]

Usage 

s_proportion_diff(
  df,
  .var,
  .ref_group,
  .in_ref_col,
  variables = list(strata = NULL),
  conf_level = 0.95,
  method = c("waldcc", "wald", "cmh", "ha", "newcombe", "newcombecc", "strat_newcombe",
    "strat_newcombecc"),
  weights_method = "cmh"
)

a_proportion_diff(
  df,
  .var,
  .ref_group,
  .in_ref_col,
  variables = list(strata = NULL),
  conf_level = 0.95,
  method = c("waldcc", "wald", "cmh", "ha", "newcombe", "newcombecc", "strat_newcombe",
    "strat_newcombecc"),
  weights_method = "cmh"
)

estimate_proportion_diff(
  lyt,
  vars,
  na_str = NA_character_,
  nested = TRUE,
  ...,
  var_labels = vars,
  show_labels = "hidden",
  table_names = vars,
  .stats = NULL,
  .formats = NULL,
  .labels = NULL,
  .indent_mods = NULL
)

Arguments

df

(data.frame)
data set containing all analysis variables.

.var

(string)
single variable name that is passed by rtables when requested by a statistics function.

.ref_group

(data.frame or vector)
the data corresponding to the reference group.

.in_ref_col

(logical)
TRUE when working with the reference level, FALSE otherwise.

variables

(named list of string)
list of additional analysis variables.

conf_level

(proportion)
confidence level of the interval.

method

(string)
the method used for the confidence interval estimation.

weights_method

(string)
weights method. Can be either "cmh" or "heuristic" and directs the way weights are estimated.

lyt

(layout)
input layout where analyses will be added to.

vars

(character)
variable names for the primary analysis variable to be iterated over.

na_str

(string)
string used to replace all NA or empty values in the output.

nested

(flag)
whether this layout instruction should be applied within the existing layout structure if possible (TRUE, the default) or as a new top-level element (FALSE). Ignored if it would nest a split. underneath analyses, which is not allowed.

...

arguments passed to s_proportion_diff().

var_labels

(character)
character for label.

show_labels

(string)
label visibility: one of "default", "visible" and "hidden".

table_names

(character)
this can be customized in case that the same vars are analyzed multiple times, to avoid warnings from rtables.

.stats

(character)
statistics to select for the table.

.formats

(named character or list)
formats for the statistics. See Details in analyze_vars for more information on the "auto" setting.

.labels

(named character)
labels for the statistics (without indent).

.indent_mods

(named integer)
indent modifiers for the labels. Defaults to 0, which corresponds to the unmodified default behavior. Can be negative.

Value

  • s_proportion_diff() returns a named list of elements diff and diff_ci.

  • estimate_proportion_diff() returns a layout object suitable for passing to further layouting functions, or to rtables::build_table(). Adding this function to an rtable layout will add formatted rows containing the statistics from s_proportion_diff() to the table layout.

Functions

  • s_proportion_diff(): Statistics function estimating the difference in terms of responder proportion.

  • a_proportion_diff(): Formatted analysis function which is used as afun in estimate_proportion_diff().

  • estimate_proportion_diff(): Layout-creating function which can take statistics function arguments and additional format arguments. This function is a wrapper for rtables::analyze().

Note

When performing an unstratified analysis, methods "cmh", "strat_newcombe", and "strat_newcombecc" are not permitted.

See also

d_proportion_diff()

Examples 

# Summary

## "Mid" case: 4/4 respond in group A, 1/2 respond in group B.
nex <- 100 # Number of example rows
dta <- data.frame(
  "rsp" = sample(c(TRUE, FALSE), nex, TRUE),
  "grp" = sample(c("A", "B"), nex, TRUE),
  "f1" = sample(c("a1", "a2"), nex, TRUE),
  "f2" = sample(c("x", "y", "z"), nex, TRUE),
  stringsAsFactors = TRUE
)

s_proportion_diff(
  df = subset(dta, grp == "A"),
  .var = "rsp",
  .ref_group = subset(dta, grp == "B"),
  .in_ref_col = FALSE,
  conf_level = 0.90,
  method = "ha"
)
#> $diff
#> [1] -8.05153
#> attr(,"label")
#> [1] "Difference in Response rate (%)"
#> 
#> $diff_ci
#> [1] -25.754477   9.651418
#> attr(,"label")
#> [1] "90% CI (Anderson-Hauck)"
#> 

# CMH example with strata
s_proportion_diff(
  df = subset(dta, grp == "A"),
  .var = "rsp",
  .ref_group = subset(dta, grp == "B"),
  .in_ref_col = FALSE,
  variables = list(strata = c("f1", "f2")),
  conf_level = 0.90,
  method = "cmh"
)
#> $diff
#> [1] -8.240459
#> attr(,"label")
#> [1] "Difference in Response rate (%)"
#> 
#> $diff_ci
#> [1] -24.002675   7.521757
#> attr(,"label")
#> [1] "90% CI (CMH, without correction)"
#> 

a_proportion_diff(
  df = subset(dta, grp == "A"),
  .var = "rsp",
  .ref_group = subset(dta, grp == "B"),
  .in_ref_col = FALSE,
  conf_level = 0.90,
  method = "ha"
)
#> RowsVerticalSection (in_rows) object print method:
#> ----------------------------
#>   row_name formatted_cell indent_mod                       row_label
#> 1     diff           -8.1          0 Difference in Response rate (%)
#> 2  diff_ci   (-25.8, 9.7)          1         90% CI (Anderson-Hauck)

l <- basic_table() %>%
  split_cols_by(var = "grp", ref_group = "B") %>%
  estimate_proportion_diff(
    vars = "rsp",
    conf_level = 0.90,
    method = "ha"
  )

build_table(l, df = dta)
#>                                   B        A      
#> ——————————————————————————————————————————————————
#> Difference in Response rate (%)           -8.1    
#>   90% CI (Anderson-Hauck)             (-25.8, 9.7)