Carrion-i Silvestre et al. (2005)

Dear Users,

I am a phd student. I want to run Carrion-i Silvestre et al. (2005) test. I tried to follow the steps on this page (https://www.aptech.com/blog/panel-data-stationarity-test-with-structural-breaks/).  But it gives me an error.

G0025 : Undefined symbol: 'm' [pankpss.src, line 44]

The code on that line is:

m_tb = zeros (1,m);

 

I don't know what is wrong or how to fix the code so if anyone can fix it I would be extremely grateful. Thank you for your time.

 

Also all code is as follows:

#include carrion.sdf

proc (4) = pankpss(data, model, model0, kernel, maxlags, struct breakControl bCtl);
local k, bigt, z, q, x, p, numkpss, denkpss, m_lee_est, m_tb, m_tb2, j,
datevec, nbreak, mbic, mlwz, supfl, dateseq, ftest, wftest, reparv, nbr, test_hom, test_het,
test_var, test_mean,  kpsstest, num, den, tb, temp1, temp2, testd_hom, testd_het;

// Number of countries
k = cols(data);

// Number of time periods
bigt = rows(data);

if model == 1 or model == 3;
// Matrix conformeb by the elements that are allowed to change
z = ones(bigt, 1);

// Number of regressors
q = cols(z);

// No x or lags
x = 0;
p = 0;

elseif model == 2 or model == 4;

// Matrix conformeb by the elements that are allowed to change
// includes time trend
z = ones(bigt, 1)~seqa(1, 1, bigt);

// Number of regressors
q = cols(z);

// No x or lags
x = 0;
p = 0;
endif;

// Storeage matrices of results
numkpss = zeros(k, 1);
denkpss = zeros(k, 1);
m_lee_est = zeros(k, 4);
m_tb = zeros(1, m);
m_tb2 = zeros(1, m);

j = 1;
do until j>k;

{ datevec, nbreak, mbic, mlwz, supfl, dateseq, ftest, wftest, reparv } = pbreak(bigt, data[.,j], z, x, p, q, m, bCtl);

nbr = mlwz;

if nbr > 0;
tb = selif(datevec[.,nbr], datevec[.,nbr] .gt 0);
{ kpsstest, num, den } = _pankpss(data[., j], tb, model, kernel, maxlags);
elseif nbr == 0;
{ kpsstest, num, den } = _pankpss(data[., j], 0, model0, kernel, maxlags);
endif;

numkpss[j] = num;
denkpss[j] = den;
m_lee_est[j, .] = kpsstest~nbr~mbic~mlwz;

m_tb = m_tb|datevec;
m_tb2 = m_tb2|reparv;

j = j + 1;
endo;

// Assuming homogenous lr variance
test_hom = meanc(numkpss)./meanc(denkpss);

// Assuming heterogeneous long-run variance
test_het = meanc(m_lee_est[., 1]);

m_tb = m_tb[2:rows(m_tb), .];

test_mean = zeros(k, 1);
test_var = zeros(k, 1);

j = 1;
do until j>k;
if  m_lee_est[j, 2] > 0;
temp1 = m_tb[(j*m)-m+1:(j*m), .];
// Computes the mean and variance
temp2 = calcdem(model, temp1[., m_lee_est[j, 2]], bigt);
test_mean[j] = temp2[1];
test_var[j] = temp2[2];

elseif m_lee_est[j, 2] == 0;
// Computes the mean and variance
temp2 = calcdem(model0, 0, bigt);
test_mean[j] = temp2[1];
test_var[j] = temp2[2];
endif;
j = j + 1;
endo;

test_mean = meanc(test_mean);
test_var = meanc(test_var);

testd_hom = sqrt(k)*(test_hom-test_mean)./sqrt(test_var);
testd_het = sqrt(k)*(test_het-test_mean)./sqrt(test_var);

print "************************************";
print "Results for the PANKPSS test        ";
print "************************************";

print "Stationarity test with structural breaks (homogeneous): " testd_hom "with p-val: " cdfnc(testd_hom);
print "Stationarity test with structural breaks (heterogeneous): " testd_het "with p-val: " cdfnc(testd_het);

print "Maximum number of breaks allowed" m;
print "Matrix of individual tests" m_lee_est;
print "Number of observations" rows(data);
print "Estimated breaking points" m_tb;

retp(testd_hom, testd_het, m_lee_est, areshape(m_tb, 15|maxlags|maxlags));
endp;

Your Answer


You must login to post answers.

Have a Specific Question?

Get a real answer from a real person

Need Support?

Get help from our friendly experts.

Try GAUSS for 14 days for FREE

See what GAUSS can do for your data

© Aptech Systems, Inc. All rights reserved.

Privacy Policy