lin1_theta_eps: Candidate point evaluation for simplicial depth in the linear...

In ChrisKust/rexpar: Simplicial Depth for Explosive Autoregressive Processes

Description

This function precalculates parameters on which depth changes to restirict the region on which the depth statistic has to be evaluated on as described in Kustosz (2016), based on the roots of the residuals. Thereby not the exact candidate points are evaluated, but variations defined by +- eps.

Usage

lin1_theta_eps(dat, eps)

Arguments

dat	Data from an AR(1) Model without intercept.
eps	Parameter epsilon to define candidates close to the original parameters.

Details

The details on the idea can be found in Kustosz (2016).

Value

t1	Candidate values for theta1.
t2	Candidate values for theta2.

Author(s)

Kustosz, Christoph

References

Kustosz, C. (2016). Depth based estimators and tests for autoregressive processes with application. Ph. D. thesis. TU Dortmund.

See Also

dS_lin2,dS1_lin2,dS2_lin2,dS3_lin2, lin2_CI,est_lin2,est_nlin1

Examples

y <- RandomARMod_lin2(100, 1.001, 0, 15, "0")
thetas <- lin1_theta_eps(y, 0.01)
summary(thetas$t1)

ChrisKust/rexpar documentation built on May 6, 2019, 11:48 a.m.