Quantcast
Channel: Statalist
Viewing all articles
Browse latest Browse all 72764

error "by() option required" after ttest command

$
0
0
Dear,

I used egranger command to run Engle-Granger 2-step ECM estimation (see below), then used test and ttest command to test the short-run and long-run causality between variables. Because ttest command does not allow factor and time-series operator, I generate a new variables, named "ecm", and then ran ttest command for this new one. However, it return an error "by() option required".

I want to how to solve this problems?

Thanks for your kindly help.

Engle-Granger 2-step ECM estimation N (1st step) = 27
N (2nd step) = 25

Engle-Granger 2-step ECM
------------------------------------------------------------------------------
D.lnrgdp | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_egresid |
L1. | -.0669184 .0176676 -3.79 0.001 -.1035588 -.030278
|
lndmcy |
LD. | -.0153264 .0047487 -3.23 0.004 -.0251746 -.0054782
|
_cons | .0667865 .0021874 30.53 0.000 .0622502 .0713228
------------------------------------------------------------------------------
(est3 stored)

.
end of do-file

. test L1._egresid

( 1) L._egresid = 0

F( 1, 22) = 14.35
Prob > F = 0.0010

. test LD.lndmcy

( 1) LD.lndmcy = 0

F( 1, 22) = 10.42
Prob > F = 0.0039

. generate ecm = L1._egresid
(1 missing value generated)

. ttest ecm
by() option required
r(100);

Viewing all articles
Browse latest Browse all 72764

Trending Articles



<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>