EViews 14: Bug in ARDL equation estimation
Posted: Wed Jul 09, 2025 2:31 am
Hi,
I have been trying to estimate this equation:
equation eq_x.ardl(cov=hac) log(x) log(y) log(z) @ @TRENDBR("1999Q3") @TRENDBR("2000Q3") @TRENDBR("2005Q3") @TRENDBR("2010Q4") @TRENDBR("2012Q4") @TRENDBR("2015Q2") @TRENDBR("2020Q1")
The relevant data file is attached with this post . The data series are all sourced/processed from public providers (with variable names removed).
In EViews 13, the code runs fine and produced the required output. But in EViews 14, I get a "Near singular matrix" error. Can someone clarify if this is a bug or if there is a problem with the way I have specified in the equation?
I have been trying to estimate this equation:
equation eq_x.ardl(cov=hac) log(x) log(y) log(z) @ @TRENDBR("1999Q3") @TRENDBR("2000Q3") @TRENDBR("2005Q3") @TRENDBR("2010Q4") @TRENDBR("2012Q4") @TRENDBR("2015Q2") @TRENDBR("2020Q1")
The relevant data file is attached with this post . The data series are all sourced/processed from public providers (with variable names removed).
In EViews 13, the code runs fine and produced the required output. But in EViews 14, I get a "Near singular matrix" error. Can someone clarify if this is a bug or if there is a problem with the way I have specified in the equation?