umx_residualize: Easily residualize variables in long or wide dataframes,...

In umx: Structural Equation Modeling and Twin Modeling in R

Easily residualize variables in long or wide dataframes, returning them changed in-place.

Description

Residualize one or more variables residualized against covariates, and return a complete dataframe with residualized variable in place. Optionally, this also works on wide (i.e., twin) data. Just supply suffixes to identify the paired-wide columns (see examples).

Usage

umx_residualize(var, covs = NULL, suffixes = NULL, data)

Arguments

var	The base name of the variable you want to residualize. Alternatively, a regression formula() containing var on the lhs, and covs on the rhs
covs	Covariates to residualize on.
suffixes	Suffixes that identify the variable for each twin, i.e. c("_T1", "_T2") Up to you to check all variables are present!
data	The dataframe containing all the variables

Details

In R, residuals for a variable can be found with the following statement:

tmp = residuals(lm(var ~ cov1 + cov2, data = data, na.action = na.exclude))

This tmp variable could then be written over the old data:

umx_residualize obviates the user having to build the lm, set na.action, or replace the data. In addition, it has the powerful feature of operating on a list of variables, and of operating on wide data, expanding the var name using a set of variable-name suffixes.

Value

• dataframe with var residualized in place (i.e under its original column name)

References

• https://tbates.github.io, https://github.com/tbates/umx

See Also

Other Twin Data functions: umx_long2wide(), umx_make_TwinData(), umx_make_twin_data_nice(), umx_scale_wide_twin_data(), umx_wide2long(), umx

Examples

# Residualize mpg on cylinders and displacement
r1 = umx_residualize("mpg", c("cyl", "disp"), data = mtcars)
r2 = residuals(lm(mpg ~ cyl + disp, data = mtcars, na.action = na.exclude))
all(r1$mpg == r2)

# =============================
# = Use the formula interface =
# =============================
r1 = umx_residualize(mpg ~ cyl + I(cyl^2) + disp, data = mtcars)

# validate against using lm
r2 = residuals(lm(mpg ~ cyl + I(cyl^2) + disp, data = mtcars, na.action = na.exclude))
all(r1$mpg == r2)

# ===========================================================
# = Residualize twin data (i.e. wide or "1 family per row") =
# ===========================================================
# Make some toy "twin" data to demonstrate with
tmp = mtcars
tmp$mpg_T1  = tmp$mpg_T2  = tmp$mpg
tmp$cyl_T1  = tmp$cyl_T2  = tmp$cyl
tmp$disp_T1 = tmp$disp_T2 = tmp$disp

covs = c("cyl", "disp")
tmp= umx_residualize(var="mpg", covs=covs, suffixes=c("_T1","_T2"), data = tmp)
str(tmp[1:5, 12:17])

# ===================================
# = Residualize several DVs at once =
# ===================================
df1 = umx_residualize(c("mpg", "hp"), cov = c("cyl", "disp"), data = tmp)
df2 = residuals(lm(hp ~ cyl + disp, data = tmp, na.action = na.exclude))
all(df1$hp == df2)

umx documentation built on May 29, 2024, 5:40 a.m.