bng_panicnew#

Purpose#

Computes the pooled Pa, Pb, and PMSB tests in Bai & Ng (2010) using panel analysis of idiosyncratic and common components (PANIC) test of nonstationarity.

Format#

{ Pa_pc, Pb_pc, PMSB_pc } = bng_panicNew(y, model[, kmax, ic_factors])#

Parameters:

y (TxN matrix) – Panel data to be tested.
model (Scalar) –
Model to be implemented.

1

Constant.

2

Constant and trend.
kmax (Scalar) – Maximum number of factors. Default = 5.
ic_factors (Scalar) –
Information Criterion for optimal number of factors. Default = 1.

1

PCp criterion.

2

ICp criterion.

Returns:

Pa_pc (Scalar) – Pa statistic based on principal components with N(0,1).
Pb_pc (Scalar) – Pb statistic based on principal components with N(0,1).
PMSB_pc (Scalar) – PMSB statistic based on principal components with N(0,1).

Examples#

library tspdlib;

// Load date file
y = loadd(getGAUSSHome() $+ "pkgs/tspdlib/examples/PDe.dat");

/*
** Default
** information criterion
** and maximum number of factors.
*/

// Model with constant and trend
model = 1;
{ Pa_pc, Pb_pc, PMSB_pc } = bng_panicNew(y, model);

Source#

pd_panic.src

1	Constant.
2	Constant and trend.

1	PCp criterion.
2	ICp criterion.