Given a segmented model (typically returned by a <code>segmented</code> method), <code>broken.line</code>
 computes the fitted values (and relevant standard errors) for the specified `segmented' relationship.

broken.line

Fitting regression models where, in addition to possible linear terms, one or more covariates have segmented (i.e., broken-line or piece-wise linear) or stepmented (i.e. piece-wise constant) effects. Multiple breakpoints for the same variable are allowed.
The estimation method is discussed in Muggeo (2003, <doi:10.1002/sim.1545>) and
illustrated in Muggeo (2008, <https://www.r-project.org/doc/Rnews/Rnews_2008-1.pdf>). An approach for hypothesis testing is presented
in Muggeo (2016, <doi:10.1080/00949655.2016.1149855>), and interval estimation for the breakpoint is discussed in Muggeo (2017, <doi:10.1111/anzs.12200>).
Segmented mixed models, i.e. random effects in the change point, are discussed in Muggeo (2014, <doi:10.1177/1471082X13504721>).
Estimation of piecewise-constant relationships and changepoints (mean-shift models) is
discussed in Fasola et al. (2018, <doi:10.1007/s00180-017-0740-4>).

Vito MR Muggeo

segmented

Regression Models with Break-Points / Change-Points Estimation
(with Possibly Random Effects)

broken.line function

Fitted values for segmented relationships — broken.line

<dl>

 <dt>ogg</dt>
<dd>A fitted object of class segmented (returned by any <code>segmented</code> method).</dd>

 <dt>term</dt>
<dd>Three options. i) A named list (whose name should be one of the segmented covariates in the model <code>ogg</code>) 
 including the covariate values for which segmented predictions should be computed; ii) a character meaning 
 the name of any segmented covariate in the model (and predictions corresponding to the observed covariate values are returned); 
 iii) It can be <code>NULL</code> if the model includes a single segmented covariate (and predictions corresponding to the observed covariate values are returned).</dd>

 <dt>link</dt>
<dd>Should the predictions be computed on the scale of the link function if <code>ogg</code> is a segmented glm fit? Default to <code>TRUE</code>.</dd>

 <dt>interc</dt>
<dd>Should the model intercept be added? (provided it exists).</dd>

 <dt>se.fit</dt>
<dd>If <code>TRUE</code> also standard errors for predictions are returned.</dd>

 <dt>isV</dt>
<dd>A couple of logicals indicating if the segmented terms \((x-\psi)_+\) and \(I(x&gt;\psi)\) in the model matrix should be replaced by their smoothed counterparts when computing the standard errors. If a single logical is provided, it is applied to both terms.</dd>

 <dt>.vcov</dt>
<dd>Optional. The full covariance matrix of estimates. If <code>NULL</code> (and <code>se.fit=TRUE</code>), the matrix is computed internally via <code>vcov.segmented()</code>.</dd>

 <dt>.coef</dt>
<dd>The regression parameter estimates. If unspecified (i.e. <code>NULL</code>), it is computed internally by <code>coef(ogg)</code>.</dd>

 <dt>...</dt>
<dd>Additional arguments to be passed on to <code>vcov.segmented()</code> when computing the standard errors for the predictions, namely
 <code>is</code>, <code>var.diff</code>, <code>p.df</code>. See <code>summary.segmented</code> and <code>vcov.segmented</code>.</dd>

</dl>

broken.line: Fitted values for segmented relationships

Description

Usage

Arguments

Value

Details

See Also

Examples