lppl_estimate_rob_2s: 2nd step LPPL estimation procedure by Geraskin and Fantazzini...

In deanfantazzini/bubble: Tests for financial bubbles and explosive behavior

Description

This function performs the 2nd step of the LPPL estimation procedure by Geraskin and Fantazzini (2013) and Fantazzini (2016)

Usage

lppl_estimate_rob_2s(x, par, max.win.tc = 0.1)

Arguments

x	is a T x 1 data vector
par	is a 6 x 1 vector containing the parameters estimated in the 1st step [beta, omega, A, B, C1, C2] and which are kept fixed in the 2nd step
max.win.tc	is a scalar (in percentage terms) used to set the starting value for the critical time tc

Details

This function performs the 2nd step of the LPPL estimation procedure by Geraskin and Fantazzini (2013) and Fantazzini (2016) using the LPPL formula by Filimonov and Sornette (2013): Keeping fixed the LPPL parameters [beta, omega, A, B, C1, C2] computed in the first stage, the critical time tc is estimated in a second step by using a quasi-Newton method algorithm.

Value

par_est2 is a 1 x 1 scalar containing the estimated parameter tc

deanfantazzini/bubble documentation built on Oct. 22, 2020, 2:43 p.m.