Name

Choi — Choi Panel Unit Root Test

CALLING SEQUENCE

res = Choi(arg1,…,argn)

PARAMETERS

Input

• arg1,…, argn: arguments that can be:

• the strings:

  - 'lagorders=x' with x=%nan (if the lags for the ADF test are to be determined automatically) or a (N x 1) or (1 x N) vector of lags for the ADF test

  - 'pmax=x' with x=%nan or a number if for the maximal # of lags for the ADF test

  - 't_order=x' for the trend order with x:

     -1: no constant, no trend

• 0: a constant, no trend (default)

• 1: a constant and a trend

  - 'noprint' if the user does not want to print the results of the test

  - 'signif=x' with x the signifance level for the individual ADF tests (0.05, 0.01 or 0.1)

  - 'namevar=xx' where xx is the name of the variable in the panel (only if the data are in a 'panel data' tlist, see help paneldb)

• a time series

• a real (nxp) matrix

• a string equal to the name of a time series or a (nxp) real matrix between quotes (note that there must be several variables of this type tos be able to perform a panel unit root test)

Output

• res a results tlist with:

  - res('meth') = 'Choi'

  - res('y') = (T x k) matrix of data

  - res('t_order') = the trend order (0 or 1)

  - res('t_orderlit') = the trend order in plain english

  - res('Pm') = Fisher''s modified Statistic (for large N) : converge toward N(0,1) under H0

  - res('Z') = Inverse Normal Test : converge toward N(0,1) under H0 when N tends to infinity

  - res('Lstar') = Modified Logit Test (George 1977): converge toward N(0,1) under H0

  - res('Pm_critical') = Critical Values of the Fisher's modified Statistic (Choi, 2001) at 1%, 5% and 10%: if Pm>Ca Reject H0

  - res('Z_critical') = Critical Values of the Inverse Normal Test: at 1%, 5% and 10% : if Z<Ca Reject H0

  - res('Lstar_critical') = Critical Values of the Modified Logit Test at 1%, 5% and 10%: if Lstar<Ca Reject H0

  - res('Pm_pvalue') = Pvalue associated to the Fisher's modified Statistic

  - res('Z_pvalue') = Pvalue associated to the Inverse Normal Test

  - res('Lstar_pvalue') = Pvalue associated to the Modified Logit Test

  - res('pvalue_ADF') = Individual pvalues of individual ERS statitics based on standard DF pvalues (only for t_order=0)

  - res('tstat') = Individual statistiques of ERS tests

  - res('pi') = Individual lag order in individual ADF models

  - res('Ti') = Adjusted Individual Size

  - res('pmax') = Maximum Lag Order for individual ADF regressions

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

  - res('namey') = name of the y variable

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

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

  - res('nonna') = vector indicating position of non-NAs

DESCRIPTION

Choi(2006) test of Unit Root ("Unit Root Tests for Cross-Sectionally Correlated Panels" in Frontiers of Analysis and Applied Research, Cambridge University Press).

EXAMPLE

// load the database containing the GDP for 25 countries in the OECD over the period 1963-2003
load(GROCERDIR+'/data/gdpan_oecd.dat');
// retrieve the names of all variables in database
listvar=dblist(GROCERDIR+'/macros/grocer/db/gdpan_oecd.dat')
 
res = Choi('log('+listvar+')','pmax=4','t_order=0')
 
// Example provides the Choi test for all variables in the database, taken in logarithm, with a constant but not trend ('t_order=0'), the Lag order to be determined by the program, the maximum number of lags set to 4 (arg 'pmax=4'). 

               

AUTHOR

Christophe Hurlin 2004 / Eric Dubois 2008