dems_neat {neatStats}

Demographics

Description

Prints participant count, age mean and SD, and gender ratio, from given dataset.

Usage

dems_neat(
  data_per_subject,
  group_by = NULL,
  gender_col = NULL,
  age_col = NULL,
  male = "male",
  female = "female",
  percent = FALSE,
  round_perc = 0,
  show_fem = NULL,
  age_range = FALSE,
  age_min = NULL,
  age_max = NULL
)

Arguments

data_per_subject

Data frame from which demographics are to be calculated. Should contain columns named as "age" and as "gender" (or, alternatively, "sex"). Alternatively, these columns can be specified via the gender_col and age_col parameters. The age column must contain only numbers or NA, while gender column must contain only 1 (= male) or 2 (= female), either as numbers or as strings, or NA. Alternatively, different gender coding can be set via the parameters male and female (but 1/2 will be checked for first in any case).

group_by

Optionally the name(s) of column(s) from the data frame provided as data_per_subject to group by.

gender_col

Optionally the name of column from the data frame that contains the gender (sex) information.

age_col

Optionally the name of column from the data frame that contains the age information.

male

Alternative code for male: by default, it is the string "male". Whatever string is given, its abbreviations will also be accepted (e.g. "m"). (Lettercases do not matter, e.g. Male or MALE are both evaluated same as male.)

female

Alternative code for female: by default, it is the string "female". Whatever string is given, its abbreviations will also be accepted (e.g. "fem"). (Lettercases do not matter.)

percent

Logical. If TRUE, gender ratios (and the "unknown" ratios based on NA values) are presented as percentage. If FALSE, they are presented as counts (i.e., numbers of subjects).

round_perc

Number to round to, when using percentages.

show_fem

Logical or NULL. If TRUE, the numbers of both male and female are displayed. If FALSE, only the number of males is displayed. If NULL (default), only the number of males is displayed when there are no unknown cases, but both numbers are displayed when there are any unknown cases.

age_range

Logical, FALSE by default. If TRUE, also displays age range per group (minimum and maximum ages).

age_min

If numeric given, removes all ages below (exclusive!) the given number before any age calculation.#'

age_max

If numeric given, removes all ages above (exclusive!) the given number before any age calculation.

Details

If gender_col and/or age_col are not specified, the function will first look for columns named precisely "age" and as "gender". If either is not found, the function looks for the same names but with any lettercase (e.g. "AGE" or "Gender"). If still no "gender" column is found, the function looks for "sex" column in the same manner. If no column is found for either, all related values will be counted as "unknown" (NA).

If NA values are found in either the age or gender column, the ratio (or count) of unknown cases will be displayed everywhere. Otherwise it will simply not be displayed anywhere.

Examples

# below is an illustrative example dataset
# (the "subject" and "measure_x" columns are not used in the function)
dat = data.frame(
    subject = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10),
    conditions = c('x', 'y', 'x', 'y', 'y', 'x', 'x', 'x', 'y', 'x'),
    gender = c(2, 2, 1, 2, 1, 2, 2, 2, 1, 1),
    age = c(6, 7, 8.5, 6, 5, 16.5, 17, 16, 45.8, 77),
    measure_x = c(83, 71, 111, 70, 92, 75, 110, 111, 110, 85),
    stringsAsFactors = TRUE
)

# print demographics (age and gender) per "conditions":
dems_neat(dat, group_by = 'conditions')

# replace unlikely ages with NAs
dems_neat(dat,
          group_by = 'conditions',
          age_min = 8,
          age_max = 50)

# remove only high values, and display age ranges
dems_neat(dat,
          group_by = 'conditions',
          age_max = 45,
          age_range = TRUE)

# another dataset, with some missing values
dat = data.frame(
    subject = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10),
    conditions = c('x', 'y', 'x', 'y', 'y', 'x', 'x', 'x', 'y', 'x'),
    gender = c(2, 2, NA, NA, 1, 1, 1, 2, NA, NA),
    age = c(6, 7, 8.5, 6, 5, 16, NA, 16, 45, 77),
    measure_x = c(83, 71, 111, 70, 92, 75, 110, 111, 110, 85),
    stringsAsFactors = TRUE
)
# again print demographics per "conditions":
dems_neat(dat, group_by = 'conditions')

# another dataset, with no "age"/"gender" columns
dat = data.frame(
    subject = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10),
    conditions = c('x', 'y', 'x', 'y', 'y', 'x', 'x', 'x', 'y', 'x'),
    geschlecht = c(2, 2, NA, NA, 1, 1, 1, 2, NA, NA),
    alter = c(6, 7, 8.5, 6, 5, 16, NA, 16, 45, 77),
    measure_y = c(83, 71, 111, 70, 92, 75, 110, 111, 110, 85),
    stringsAsFactors = TRUE
)

# the following will return "unknowns"
dems_neat(dat, group_by = 'conditions')

# gender column specified
dems_neat(dat, group_by = 'conditions', gender_col = 'geschlecht')

# both columns specified
dems_neat(dat,
          group_by = 'conditions',
          age_col = 'alter',
          gender_col = 'geschlecht')