Page 1 of 1

t+1 in eviews

Posted: Tue Oct 06, 2015 9:31 am
by kerry
I'm trying to estimate a simple equation: y(t+1) = a + b*x(t)
Can I put "y(1) c x" into the estimate window? so that (1) will automatically mean t+1?
I've tried both "y(1) c x" and "y c x(-1)" to estimate, I get exactly the same output of regression from these two.
But someone told me that it would be wrong to use y(1) for y(t+1), I have to go back one period and estimate the equation using "y c x(-1)".
Can someone explain to me why? If it is wrong, why am I getting the same output for both method?

Re: t+1 in eviews

Posted: Tue Oct 06, 2015 9:35 am
by EViews Gareth
y(1) is the correct syntax for a one period lead on Y.

Re: t+1 in eviews

Posted: Tue Oct 06, 2015 9:47 am
by kerry
y(1) is the correct syntax for a one period lead on Y.
Ok but if i turn ny equation into y = a + b*x(t-1), and estimate using "y c x(-1)",
the intercept and coefficient gotten from this estimate can also be used on the original equation y(t+1)= a + b*x(t) right?
Basically these two equations are the same?

Re: t+1 in eviews

Posted: Tue Oct 06, 2015 9:50 am
by startz
y(1) is the correct syntax for a one period lead on Y.
Ok but if i turn ny equation into y = a + b*x(t-1), and estimate using "y c x(-1)",
the intercept and coefficient gotten from this estimate can also be used on the original equation y(t+1)= a + b*x(t) right?
Basically these two equations are the same?
They are the same equation, but they may differ by one observation in the data used to estimate them.

Re: t+1 in eviews

Posted: Tue Oct 06, 2015 9:54 am
by kerry
y(1) is the correct syntax for a one period lead on Y.
Ok but if i turn ny equation into y = a + b*x(t-1), and estimate using "y c x(-1)",
the intercept and coefficient gotten from this estimate can also be used on the original equation y(t+1)= a + b*x(t) right?
Basically these two equations are the same?
They are the same equation, but they may differ by one observation in the data used to estimate them.
so the correct input for my original equation will be "y(1) c x"?
if i remember correctly, few years ago when i first learnt eviews, i was told that eviews does not allow lead on y variables, tat's really strange..