Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Scott Merryman <scott.merryman@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: Re: xtunitroot ips error for 'no observations' and trend |
Date | Tue, 21 Sep 2010 08:30:51 -0500 |
Without trend, failure to reject the null of a unit root would imply that the data needs to be differenced to be stationary; if the null is rejected then the data is stationary and doesn’t need to be differenced. With trend, failure to reject implies that the data needs to be differenced to make it stationary ; if the null is not rejected the data is trend stationary and needs to be analyzed a time trend in the regression model instead of differencing. Scott On Sun, Sep 19, 2010 at 6:56 PM, wangpan110 <wangpan110@hotmail.com> wrote: > Hi Scott, 1) does the involvement of -trend- mean the unit root test account > both DSP and TSP? > 2) the involvement of trend changes the p-value substantially, > does it mean the nonstationarity of this panel/series is closely related > with TSP? if it is, what i should do? > > many thanks > > Pan * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/