f.build

<code>f.build()</code> returns a <code><a href="/link/formula?package=cobalt&version=4.5.5" data-mini-rdoc="cobalt::formula">formula</a></code> of the form <code>y ~ x1 + x2 + ...</code> from a data frame input. It can be much quicker to use <code>f.build()</code> than to hand-write the precise formula, which may contain errors. It can be used in place of a formula in, for example, <code><a href="/link/glm()?package=cobalt&version=4.5.5" data-mini-rdoc="cobalt::glm()">glm()</a></code>, <code>matchit()</code>, or <code>bal.tab()</code>. It provides similar functionality to <code><a href="/link/reformulate()?package=cobalt&version=4.5.5" data-mini-rdoc="cobalt::reformulate()">reformulate()</a></code>.

Generate balance tables and plots for covariates of groups preprocessed through
matching, weighting or subclassification, for example, using propensity scores. Includes
integration with 'MatchIt', 'WeightIt', 'MatchThem', 'twang', 'Matching', 'optmatch', 'CBPS', 'ebal',
'cem', 'sbw', and 'designmatch' for assessing balance on the output of their preprocessing
functions. Users can also specify data for balance assessment not generated through
the above packages. Also included are methods for assessing balance in clustered or
multiply imputed data sets or data sets with multi-category, continuous, or longitudinal treatments.

Noah Greifer

cobalt

Covariate Balance Tables and Plots

f.build function

<dl><dt>y</dt>
<dd>the quoted name of the response (left hand side) variable in the formula. Only one variable is supported. If missing, <code>NULL</code>, or the empty string (<code>""</code>), the formula will have no response variable. If <code>rhs</code> is not supplied, <code>y</code> will replace <code>rhs</code> and <code>y</code> will be set to <code>""</code>.</dd>
<dt>rhs</dt>
<dd>a data frame whose variable names will be the terms on the right hand side of the formula, or a character vector whose values will be the terms on the right hand side of the formula. If missing, the argument to <code>y</code> will replace <code>rhs</code> and <code>y</code> will be set to <code>""</code>; in essence, <code>f.build("x")</code> is the same as <code>f.build("", "x")</code>, both producing <code>~ x</code>.</dd></dl>

Arguments

<code>f.build()</code> returns a <code><a href='https://rdrr.io/r/stats/formula.html'>formula</a></code> of the form <code>y ~ x1 + x2 + ...</code> from a data frame input. It can be much quicker to use <code>f.build()</code> than to hand-write the precise formula, which may contain errors. It can be used in place of a formula in, for example, <code><a href='https://rdrr.io/r/stats/glm.html'>glm()</a></code>, <code>matchit()</code>, or <code>bal.tab()</code>. It provides similar functionality to <code><a href='https://rdrr.io/r/stats/delete.response.html'>reformulate()</a></code>.

Convenient Formula Generation — f.build

<dl>

<dt>y</dt>
<dd>the quoted name of the response (left hand side) variable in the formula. Only one variable is supported. If missing, <code>NULL</code>, or the empty string (<code>""</code>), the formula will have no response variable. If <code>rhs</code> is not supplied, <code>y</code> will replace <code>rhs</code> and <code>y</code> will be set to <code>""</code>.</dd>


<dt>rhs</dt>
<dd>a data frame whose variable names will be the terms on the right hand side of the formula, or a character vector whose values will be the terms on the right hand side of the formula. If missing, the argument to <code>y</code> will replace <code>rhs</code> and <code>y</code> will be set to <code>""</code>; in essence, <code>f.build("x")</code> is the same as <code>f.build("", "x")</code>, both producing <code>~ x</code>.</dd>

</dl>

f.build: Convenient Formula Generation

Description

Usage

Value

Arguments

See Also

Examples