coint_maki¶

Purpose¶

Computes the test of the null hypothesis of no cointegration against the alternative of cointegration with an unknown number of breaks.

Format¶

tst = coint_maki(y, m, model[, trimm, lagoption])¶

Parameters:

y (Nxk matrix) – Data to be tested.
m (Scalar) – Maximum number of breaks.
model (Scalar) –
Model to be implemented.

0

Level shift

1

Level shift with trend

2

Regime shift

3

Regime shift with trend
trimm (Scalar) – Optional, trimming rate. Default = 0.10.
lagoption (Scalar.) –
Optional, lag selection criteria. Default = 1.

0

No lags

1

T-stat criterion

Returns:

tst (Scalar) – Test statistic

Examples¶

/*
** This example program tests for cointegration
** with alternatives hypothesis up to m structural breaks
*/
library tspdlib;

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

// Set the maximum number of breaks
m = 3;

/*
** Set the model
**   0: level shift
**   1: level shift with trend
**   2: regime shifts
**   3: Trend and Regime shifts
*/
model = 2;

// Perform test
call coint_maki(datap, m, model);

Source¶

coint_maki.src

0	Level shift
1	Level shift with trend
2	Regime shift
3	Regime shift with trend

0	No lags
1	T-stat criterion