fourier_lm#

Purpose#

Computes the LM unit root test with flexible Fourier form structural breaks.

Format#

{ LMk, f, p, cv } = Fourier_LM(y[, pmax, fmax, ic])#

Parameters:

y (Nx1 matrix) – Dependent variable.
pmax (Scalar) – Optional, maximum number of lags for \(\Delta y\); 0=no lag. Default = 8.
fmax (Scalar) – Optional, maximum number of single Fourier frequency (upper bound is 5). Default = 5.
ic (Scalar) –
Optional, the information criterion used for choosing lags. Default = 3.

1

Akaike.

2

Schwarz.

3

t-stat significance.

Returns:

lmk (Scalar) – LM(k) statistic.
f (Scalar) – Number of single frequency.
p (Scalar) – number of lags selected by chosen information criterion
cv (Vector) – 1%, 5%, 10% critical values for the chosen model

Examples#

library tspdlib;

// Load date file
y = loadd(getGAUSSHome() $+ "pkgs/tspdlib/examples/ts_examples.csv", "Y + date($Date, '%b-%y')");

// Call test
{ LMstat, f, p, cv } = Fourier_LM(y);

Source#

fourier_lm.src

1	Akaike.
2	Schwarz.
3	t-stat significance.