Descriptive summaries without hypothesis tests

Compute continuous or categorical summaries with explicit denominators and missing counts using standard R.

Usage

describe_data(data, variables = setdiff(names(data), group), group = NULL,
  labels = NULL, units = NULL, types = NULL)

Arguments

data

A data frame.

variables

Distinct column names to summarize.

group

Optional single grouping column name. Missing groups are retained explicitly.

labels, units

Optional named display metadata keyed by variable name.

types

Optional named continuous/categorical overrides. Ordered factors are categorical by default.

Details

Numeric summaries are mean, sample standard deviation, median, quartiles (type 7), minimum and maximum. Categorical proportions use nonmissing observations within each group as their denominator; n.missing and n.total remain separate. Empty populations produce explicit unavailable summaries. Infinite measurements are rejected. No hypothesis tests or automatic p-value columns are calculated.

Value

A descriptive_result inheriting from inference_result.

Examples

describe_data(data.frame(value = c(1, 3, NA), category = factor(c("a", "b", "a"))))
#> <descriptive> descriptive_summary
#>             row_id estimand estimate p.reported status
#>  description:1:1:1     mean 2.000000         NA     ok
#>  description:1:1:2       sd 1.414214         NA     ok
#>  description:1:1:3   median 2.000000         NA     ok
#>  description:1:1:4       q1 1.500000         NA     ok
#>  description:1:1:5       q3 2.500000         NA     ok
#>  description:1:1:6      min 1.000000         NA     ok
#>  description:1:1:7      max 3.000000         NA     ok
#>  description:2:1:8    count 2.000000         NA     ok
#>  description:2:1:9    count 1.000000         NA     ok