vcov.stepmented: Variance-Covariance Matrix for a Fitted Segmented Model

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

Variance-Covariance Matrix for a Fitted Segmented Model

Description

Returns the variance-covariance matrix of the parameters (including breakpoints) of a fitted stepmented model object.

Usage

## S3 method for class 'stepmented'
vcov(object, k=NULL, ...)

Arguments

object	a fitted model object of class "stepmented", returned by any stepmented method
k	The power of n for the smooth approximation. Simulation evidence suggests k in [-1, -1/2]; with k=-1/2 providing somewhat 'conservative' standard errors especially at small sample sizes.
...	additional arguments.

Details

The full covariance matrix is based on the smooth approximation

I(x>\psi)\approx \Phi((x-\psi)/n^{k})

via the sandwich formula using the empirical information matrix. \Phi(\cdot) is the standard Normal cdf, and k is the argument k. When k=NULL (default), it is computed via

k=-(0.6 + 0.3 \ \log(snr) - (|\hat\psi-0.5|/n)^{1/2})

where snr is the signal-to-noise ratio corresponding to the estimated changepoint \hat\psi (in the range (0,1)). The above formula comes from extensive simulation study under different scenarios.

Value

The full matrix of the estimated covariances between the parameter estimates, including the breakpoints.

Note

If the fit object has been called by stepmented(.., var.psi=TRUE), then vcov.stepmented will return object$vcov, unless the power k differs from -2/3.

Author(s)

Vito Muggeo

See Also

stepmented

Examples

##see ?stepmented

segmented documentation built on Nov. 28, 2023, 1:07 a.m.