Is your question related to the approach suggested, among others, by Shin et al.? If you mean this one, the answer is &quot;yes&quot;.<br>Actually you simply need to decompose your series of interest into the positive and negative partial sum processes using e.g.<br>
<br>smpl $i &gt; 0 --restrict<br><br>command and estimate a single-equation ECM as usual.<br><br>Artur<br><br><br><div class="gmail_quote">Am 3. April 2012 17:42 schrieb Hanne holopainen <span dir="ltr">&lt;<a href="mailto:nevalaine1@gmail.com">nevalaine1@gmail.com</a>&gt;</span>:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Hi everybody !<br><br>I am a beginner as a user of Gretl and I would be very pleased if someone could help me with a few details. Especially I am interested in possibilities offered by Gretl to make an asymmetric error correction model. I have not been able to find a way to divide my data, or in fact explanatory variables, on the basis of their sign (positive/negative), so that both positive and negative values of them would be in the model at the same time . Is it possible in Gretl at all ? <br>

<br>Sincerely,<br><br>Hanne<br>
<br>_______________________________________________<br>
Gretl-users mailing list<br>
<a href="mailto:Gretl-users@lists.wfu.edu">Gretl-users@lists.wfu.edu</a><br>
<a href="http://lists.wfu.edu/mailman/listinfo/gretl-users" target="_blank">http://lists.wfu.edu/mailman/listinfo/gretl-users</a><br></blockquote></div><br>