johansen_beta_part Johansen cointegration mmethod johansen_eigen

Grocer >> Johansen cointegration mmethod > johansen_common_beta

johansen_common_beta

impose and test common restrictions on the cointegration relations

CALLING SEQUENCE

[res]=johansen_common_beta(res,nbrel,H,arg1,…,argn)

PARAMETERS

Input

• res = a johansen result tlist

• nbrel = a scalar, the # cointegration relations

• H = a (n x k) matrix doing making the passage from the free parameters to the constrained ones

• argi: arguments which can be:

 * the string 'NBoot=n' where n is the number of bootstrap draws (default: 999)

 * the string 'noprint' if the user doesn't want the to print the results of the regression

Output

• res =a results tlist:

  -res('namey') = the name of the variables (m x 1)

  -res('y') = matrix of values for the variables (m x 1)

  -res('namexo_lt') = the names of the exogenous variables in the cointegrating vectors

  -res('exo_lt') = the matrix of the exogenous variables in the cointegrating vectors

  -res('namexo_st') = the names of the exogenous variables in the short run dynamics of the VAR

  -res('exo_st') = the matrix of the exogenous variables in the short run dynamics of the VAR

  -res('dy') = the matrix of the differentiated endogenous variables

  -res('exo') = the matrix of the variables in the short run dynamics (lagged differentiated endogenous variables + short run exogenous variables)

  -res('lagy') = the matrix of the variables in the cointegrating relations (lagged endogenous variables + long run exogenous variables)

  -res('nobs') = # of observations

  -res('nvar') = # of variables

  -res('nlags') = # of lags of the VAR

  -res('eig') = eigenvalues (m x 1)

  -res('evec') = eigenvectors (m x m)

  -res('pi') = coefficients of the short run dynamics

  -res('lr1') = likelihood ratio trace statistic for r=0 to m-1 (m x 1) vector

  -res('lr2') = maximum eigenvalue statistic for r=0 to m-1 (m x 1) vector

  -res('dropna') = boolean indicating if NAs have been dropped

  -res('nonna') = vector indicating position of non-NA values (if the option 'dropna' was active)

  -res('max non zeros') = maximum number of zeros a variable had to be considered as a dummy

  -res('NBoot') = # of bootstrap draws

  -res('alpha') = value of the error correction coefficients

  -res('cvt') = critical values for trace statistic (m x 3) vector [90% 95% 99%]

  -res('cvm') = critical values for max eigen value statistic (3 x m) vector [90% 95% 99%]

  -res('p trace') = p-value for the trace statistic calculated with the standard bootstrap method

  -res('p lmax') = p-value for the lambda-max statistic calculated with the standard bootstrap method

  -res('p double trace') = p-value for the trace statistic calculated with the double bootstrap method

  -res('p double lmax') = p-value for the lambda-max statistic calculated with the double bootstrap method

  -res('prests') = boolean indicating the presence or absence of a time series in the regression

  -res('bounds') = if there is a time series in the regression, the bounds of the regression

  - res('nb of cointegration relations') = # of cointegration relations used for the test

  - res('test type') = 'some ec vectors imposed'

  - res('test stat') = value of the statistical test

  - res('bootstrap test pvalue') = the p-value of the test statistic calculated with the standard bootstrap method

  - res('fast double bootstrap test pvalue')= the p-value of the test statistic calculated with the double bootstrap method

  - res('H') = matrix that transforms the free parameters into the constrained ones

  - res('test nb of draws')=NBoot

DESCRIPTION

In the Johansen procedure, impose and test common restrictions on the cointegration relations (beta coefficients).

EXAMPLE

load(GROCERDIR+'\data\juselius.dat')
// create dummies used for regression p.111-112
post83q1=dummy(['1973q1';'2003q1'],['1983q1';'2003q1']);
dum75q4=dummy(['1973q1';'2003q1'],'1975q4')-0.5*dummy(['1973q1';'2003q1'],['1976q1';'1976q2']);
dum76q4=dummy(['1973q1';'2003q1'],'1976q4');
dum83q2=dummy(['1973q1';'2003q1'],'1983q2');
dum83q1=dummy(['1973q1';'2003q1'],'1983q1');

rj1=johansen(1,'dnk_Lm3rC','dnk_Lyr','dnk_DLpy','dnk_Rm','dnk_Rb','exo_lt=trend^1;post(1983q1)','exo_st=const;dum75q4;dum76q4;dum83q1')
 
H1=zeros(7,6);
for i=1:5
   H1(i,i)=1;
end
H1(7,6)=1
rjtest1=johansen_common_beta(rj1,3,H1)
 
 
// Example taken from function johansen_d(). The first argument is the name of the result tlist stemming from a johansen estimation on Danish data. The number of cointegration relations is set to 2. The restrictions on the beta parameters are given by the matrix H1.

AUTHOR

Eric Dubois 2009
johansen_beta_part Johansen cointegration mmethod johansen_eigen