Skip to contents

Summary numeric variables in columns

Source: R/summarize_variables_in_cols.R
summarize_variables_in_columns.Rd

[Experimental]

These functions can be used to produce summary tables for PK datasets.

Usage

summary_in_cols(x, labelstr = "", custom_label = NULL)

# S3 method for numeric
summary_in_cols(x, labelstr = "", custom_label = NULL, ...)

# S3 method for factor
summary_in_cols(x, labelstr = "", custom_label = NULL, ...)

# S3 method for character
summary_in_cols(x, labelstr = "", custom_label = NULL, ...)

# S3 method for logical
summary_in_cols(x, labelstr = "", custom_label = NULL, ...)

summarize_vars_in_cols(
  lyt,
  var,
  var_type = "numeric",
  ...,
  .stats = c("n", "mean", "sd", "se", "cv", "geom_cv"),
  .labels = c(n = "n", mean = "Mean", sd = "SD", se = "SE", cv = "CV (%)", geom_cv =
    "CV % Geometric Mean"),
  .formats = NULL,
  .indent_mods = NULL,
  col_split = TRUE
)

Arguments

x

(numeric)
vector of numbers we want to analyze.

labelstr

(character)
label of the level of the parent split currently being summarized (must be present as second argument in Content Row Functions).

custom_label

(string or NULL)
if provided and labelstr is empty then this will be used as the row label.

...

additional arguments for the lower level functions.

lyt

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

var

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

var_type

Variable type, "numeric" by default.

.stats

(character)
statistics to select for the table.

.labels

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

.formats

(named character or list)
formats for the statistics.

.indent_mods

(named integer)
indent modifiers for the labels.

col_split

(flag)
whether the columns should be split.

Value

A named list of all statistics returned by s_summary.numeric(). See s_summary.numeric() to be aware of all available statistics.

A named list of all statistics returned by s_summary.factor(). See s_summary.factor() to be aware of all available statistics.

A named list of all statistics returned by s_summary.character(). See s_summary.character() to be aware of all available statistics.

A named list of all statistics returned by s_summary.logical(). See s_summary.logical() to be aware of all available statistics.

Functions

  • summary_in_cols(): summary_in_cols is a S3 generic function to produce an object description.

  • summary_in_cols(numeric): a wrapper of s_summary.numeric() function that produces a named list of statistics to include as columns.

  • summary_in_cols(factor): a wrapper of s_summary.factor() function that produces a named list of statistics to include as columns.

  • summary_in_cols(character): a wrapper of s_summary.character() function that produces a named list of statistics to include as columns.

  • summary_in_cols(logical): a wrapper of s_summary.logical() function that produces a named list of statistics to include as columns.

  • summarize_vars_in_cols(): Layout creating function which can be used for creating summary tables in columns, primarily used for PK data sets.

See also

summarize_vars.

Examples


library(scda)
library(dplyr)
ADPP <- scda::synthetic_cdisc_data("latest")$adpp %>% h_pkparam_sort()
summary_in_cols(ADPP$AGE, custom_label = "stats")
#> $n
#>     n 
#> 26268 
#> attr(,"label")
#> [1] "stats"
#> 
#> $sum
#>    sum 
#> 916014 
#> attr(,"label")
#> [1] "stats"
#> 
#> $mean
#>     mean 
#> 34.87186 
#> attr(,"label")
#> [1] "stats"
#> 
#> $sd
#>       sd 
#> 7.364059 
#> attr(,"label")
#> [1] "stats"
#> 
#> $se
#>         se 
#> 0.04543638 
#> attr(,"label")
#> [1] "stats"
#> 
#> $mean_sd
#>      mean        sd 
#> 34.871859  7.364059 
#> attr(,"label")
#> [1] "stats"
#> 
#> $mean_se
#>        mean          se 
#> 34.87185930  0.04543638 
#> attr(,"label")
#> [1] "stats"
#> 
#> $mean_ci
#> mean_ci_lwr mean_ci_upr 
#>    34.78280    34.96092 
#> attr(,"label")
#> [1] "stats"
#> 
#> $mean_sei
#> mean_sei_lwr mean_sei_upr 
#>     34.82642     34.91730 
#> attr(,"label")
#> [1] "stats"
#> 
#> $mean_sdi
#> mean_sdi_lwr mean_sdi_upr 
#>     27.50780     42.23592 
#> attr(,"label")
#> [1] "stats"
#> 
#> $mean_pval
#> p_value 
#>       0 
#> attr(,"label")
#> [1] "stats"
#> 
#> $median
#> median 
#>     34 
#> attr(,"label")
#> [1] "stats"
#> 
#> $mad
#> mad 
#>   0 
#> attr(,"label")
#> [1] "stats"
#> 
#> $median_ci
#> median_ci_lwr median_ci_upr 
#>            34            34 
#> attr(,"conf_level")
#> [1] 0.9509612
#> attr(,"label")
#> [1] "stats"
#> 
#> $quantiles
#> quantile_0.25 quantile_0.75 
#>            30            39 
#> attr(,"label")
#> [1] "stats"
#> 
#> $iqr
#> iqr 
#>   9 
#> attr(,"label")
#> [1] "stats"
#> 
#> $range
#> min max 
#>  20  69 
#> attr(,"label")
#> [1] "stats"
#> 
#> $min
#> min 
#>  20 
#> attr(,"label")
#> [1] "stats"
#> 
#> $max
#> max 
#>  69 
#> attr(,"label")
#> [1] "stats"
#> 
#> $cv
#>       cv 
#> 21.11748 
#> attr(,"label")
#> [1] "stats"
#> 
#> $geom_mean
#> geom_mean 
#>  34.13964 
#> attr(,"label")
#> [1] "stats"
#> 
#> $geom_mean_ci
#> mean_ci_lwr mean_ci_upr 
#>    34.05518    34.22432 
#> attr(,"label")
#> [1] "stats"
#> 
#> $geom_cv
#> geom_cv 
#> 20.7003 
#> attr(,"label")
#> [1] "stats"
#> 

lyt <- basic_table() %>%
  split_rows_by(var = "ARM", label_pos = "topleft") %>%
  split_rows_by(var = "SEX", label_pos = "topleft") %>%
  summarize_vars_in_cols(var = "AGE", col_split = TRUE)
result <- build_table(lyt = lyt, df = ADPP)
result
#> ARM                                                                    
#>   SEX             n     Mean   SD    SE    CV (%)   CV % Geometric Mean
#> ———————————————————————————————————————————————————————————————————————
#> A: Drug X                                                              
#>   F              5214   32.8   6.0   0.1    18.5           18.7        
#>   M              3630   35.2   6.9   0.1    19.6           19.7        
#> B: Placebo                                                             
#>   F               0      NA    NA    NA      NA             NA         
#>   M               0      NA    NA    NA      NA             NA         
#> C: Combination                                                         
#>   F              9240   35.2   7.3   0.1    20.8           20.4        
#>   M              8184   35.7   8.1   0.1    22.7           21.9        

# By selecting just some statistics and ad-hoc labels
lyt <- basic_table() %>%
  split_rows_by(var = "ARM", label_pos = "topleft") %>%
  split_rows_by(var = "SEX", label_pos = "topleft") %>%
  summarize_vars_in_cols(
    var = "AGE",
    .stats = c("n", "cv", "geom_mean", "mean_ci", "median", "min", "max"),
    .labels = c(
      n = "myN",
      cv = "myCV",
      geom_mean = "myGeomMean",
      mean_ci = "Mean (95%CI)",
      median = "Median",
      min = "Minimum",
      max = "Maximum"
    ),
    col_split = TRUE
  )
result <- build_table(lyt = lyt, df = ADPP)
result
#> ARM                                                                                    
#>   SEX            myN    myCV   myGeomMean    Mean (95%CI)    Median   Minimum   Maximum
#> ———————————————————————————————————————————————————————————————————————————————————————
#> A: Drug X                                                                              
#>   F              5214   18.5      32.2      (32.60, 32.92)    32.0     21.0      47.0  
#>   M              3630   19.6      34.6      (34.99, 35.44)    34.0     23.0      50.0  
#> B: Placebo                                                                             
#>   F               0      NA        NA             NA           NA       NA        NA   
#>   M               0      NA        NA             NA           NA       NA        NA   
#> C: Combination                                                                         
#>   F              9240   20.8      34.5      (35.05, 35.35)    35.0     21.0      64.0  
#>   M              8184   22.7      34.8      (35.52, 35.87)    35.0     20.0      69.0  

lyt <- basic_table() %>%
  summarize_vars_in_cols(
    var = "AGE",
    col_split = TRUE,
    custom_label = "some custom label"
  )
result <- build_table(lyt, df = ADPP)
result
#>                       n     Mean   SD    SE    CV (%)   CV % Geometric Mean
#> ———————————————————————————————————————————————————————————————————————————
#> some custom label   26268   34.9   7.4   0.0    21.1           20.7        

# PKPT03
lyt <- basic_table() %>%
  split_rows_by(var = "TLG_DISPLAY", split_label = "PK Parameter", label_pos = "topleft") %>%
  summarize_vars_in_cols(
    var = "AVAL",
    col_split = TRUE,
    .stats = c("n", "mean", "sd", "cv", "geom_mean", "geom_cv", "median", "min", "max"),
    .labels = c(
      n = "n",
      mean = "Mean",
      sd = "SD",
      cv = "CV (%)",
      geom_mean = "Geometric Mean",
      geom_cv = "CV % Geometric Mean",
      median = "Median",
      min = "Minimum",
      max = "Maximum"
    )
  )
result <- build_table(lyt, df = ADPP)
result
#> PK Parameter    n     Mean     SD    CV (%)   Geometric Mean   CV % Geometric Mean   Median   Minimum   Maximum
#> ———————————————————————————————————————————————————————————————————————————————————————————————————————————————
#> Cmax           2388   30.1    6.1     20.4         29.5               22.0            30.1     10.1      48.9  
#> AUCinf obs     2388   199.3   39.8    19.9        195.1               21.3           198.6     71.5      323.5 
#> CL obs         2388    5.0    1.0     20.0         4.9                21.4            5.0       1.3       8.4  
#> Ae             4776    1.6    0.3     20.0         1.5                21.0            1.6       0.6       2.6  
#> Fe             4776   15.6    3.1     19.9         15.3               21.2            15.6      4.3      26.4  
#> CLR            2388    0.0    0.0     20.2         0.0                21.9            0.0       0.0       0.1  
#> Rmax           2388   10.0    2.0     19.5         9.8                20.7            10.0      3.2      17.3  
#> Tonset         2388    3.0    0.6     19.8         2.9                21.2            3.0       1.1       5.0  
#> RENALCLD       2388    0.0    0.0     19.6         0.0                21.3            0.0       0.0       0.0