HTUNIT Procedure

@HTUNIT implements the panel unit root tests from Harris and Tzavalis(1999). This uses large N, fixed T asymptotics, correcting the unit root tests for sample sample bias.

@HTUnit( options ) series start end

Parameters

series	series to analyze
start, end	range of series to use. By default, the defined range of series.

Options

DET=NONE/[CONSTANT]/TREND

Individual-specific deterministic components to remove

SMPL=standard SMPL option[not used]

TITLE="title for output" ["Harris-Tzavalis Test: Series ..."]

[PRINT]/NOPRINT

Variables Defined

%CDSTAT	the H-T test statistic (REAL)
%SIGNIF	the significance level of %CDSTAT as a one-tailed N(0,1) (REAL)
%NGROUP	number of individuals (INTEGER)

Example

This does an H-T test on the OECD country data from the Penn World tables, applying it to the log real exchange rate with time effects removed.

open data pennxrate.dta

calendar(panelobs=34,a) 1970

data(format=dta) 1//1970:01 151//2003:01 year xrate ppp id capt realxrate lnrxrate oecd g7

panel(entry=1.0,time=-1.0,smpl=oecd) lnrxrate / cxrate

@htunit(title="Harris-Tzavalis test on log real exchange rate",smpl=oecd) cxrate

Sample Output

This is the output from the example. The null of a unit root is rather strongly rejected.

Harris-Tzavalis test on log real exchange rate

Test has fixed T, large N asymptotics

Null is rho(i)=1. Alternative is rho(i)==rho<>1

Individual Specific Components: Constant

N 27

T 34

Rho 0.7314

Z -10.5915

Signif 0.0000