dh.makeIQR: Transforms variables based on their interquartile range

In lifecycle-project/ds-cs-functions: Helper Functions for Use with 'DataSHIELD'

Transforms variables based on their interquartile range

Description

This function scales variables by their interquartile range. IQR is calulcated either within cohort or using the combined IQR across cohorts. The formula used is: value_subject / (75th percentile - 25th percentile).

Usage

dh.makeIQR(
  df = NULL,
  vars = NULL,
  type = c("combine", "split"),
  new_obj = df,
  conns = NULL,
  checks = TRUE,
  new_df_name = NULL
)

Arguments

df	Character specifying a server-side data frame.
vars	Character vector of columns within df to transform.
type	Use "combine" to transform the variable based on the combined IQR across all cohorts specified in conns, or "split" to transform based on the within-cohort IQR.
new_obj	Character specifying name for created serverside object.
conns	DataSHIELD connections object.
checks	Logical; if TRUE checks are performed prior to running the function. Default is TRUE.
new_df_name	Retired argument. Please use ‘new_obj’ instead.

Value

Server-side object specified in df with transformed variables added as columns. Variables have suffix "_iqr_c" if type is "combine", or "_iqr_s" if type is "split".

See Also

Other data manipulation functions: dh.makeAgePolys(), dh.quartileSplit(), dh.zByGroup()

lifecycle-project/ds-cs-functions documentation built on Nov. 18, 2024, 3:36 p.m.