Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: Re: RE: problems about madfuller package


From   "Nick Cox" <[email protected]>
To   <[email protected]>
Subject   st: RE: Re: RE: problems about madfuller package
Date   Tue, 19 Apr 2005 15:54:26 +0100

OK, so that's seemingly not the explanation. 

As reported, the original example in the help file 
works fine with me. See below. So, I don't have 
any more ideas here. 

.  use http://fmwww.bc.edu/ec-p/data/hayashi/sheston91.dta,clear
(Penn World Table Mark 5, R. Summers / A. Heston, 1991)

.  madfuller rgdppc if country<11, lags(2(2)8)

Multivariate Augmented Dickey-Fuller test for rgdppc
with 26 observations on 10 cross-sectional units
-----------------------------------------------------------
       Obs    Lags        MADF      Approx 5% CV
-----------------------------------------------------------
        24       2      41.274         31.844
        22       4      45.038         34.737
        20       6      30.610         38.897
        18       8      51.578         45.195
-----------------------------------------------------------
H0: all 10 timeseries in the panel are I(1) processes

.  madfuller D.rgdppc if country<11, lags(4)

Multivariate Augmented Dickey-Fuller test for D.rgdppc
with 25 observations on 10 cross-sectional units
-----------------------------------------------------------
       Obs    Lags        MADF      Approx 5% CV
-----------------------------------------------------------
        21       4      82.132         36.616
-----------------------------------------------------------
H0: all 10 timeseries in the panel are I(1) processes

Nick 
[email protected] 

www

> I have update all the ado file and executable file.
> But the same problem occurs.
> When using madfuller package, are there any other packages 
> also required?
> I use the levinlin package, it works fine.
> But madfuller doesn't.

Nick Cox
 
> > This is the test example for Kit Baum's
> > -madfuller- from SSC. It works fine for
> > me. I suspect some different problem,
> > such as your Stata not being fully up-to-date.
> > -update all- and try again.

www, a.k.a Terence

> > > While using madfuller to test panel unit root,
> > > I use the example provided by this package.
> > > Those commands I use are following:
> > >
> > > use  http://fmwww.bc.edu/ec-p/data/hayashi/sheston91.dta,clear
> > > tsset country year, yearly
> > > madfuller rgdppc if country<11, lags(2(2)8)
> > >
> > > But I got error message like 'variable __000001 not found' or
> > > ' variable
> > > year not found'
> > > Does anyone have same experience like this?
> > > Or the commands I set are wrong?

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index