8:56 a.m.
Hi,
after estimating a LOGIT model I obtain the following message:
"Note: armeu == 0 predicts failure perfectly
714 observations not used
Not a Number in calculation"
I used the command "catch logit ..." to control for any error. I am
wondered why the $error flag is still zero despite the message. Should
this not result in a non-zero error value?
Best,
Artur
3 a.m.
On Thu, Aug 22, 2013 at 4:56 AM, Artur Tarassow
after estimating a LOGIT model I obtain the following message:
"Note: armeu == 0 predicts failure perfectly
714 observations not used
Not a Number in calculation"
I used the command "catch logit ..." to control for any error. I am
wondered why the $error flag is still zero despite the message. Should
this not result in a non-zero error value?
Artur, could you please send (offlist if the data are big) your data and
script?
In a simple case of perfect prediction I'm getting a non-zero $error
OK (example below) but apparently the case you're looking at is
more complicated.
<hansl>
nulldata 100
series x1 = normal()
series ndx = 1.5 + 2*x1
series y = ndx > 0
catch logit y 0 x1
err = $error
if err
printf "err = %d (%s)\n", err, errmsg(err)
else
print "no error"
endif
</hansl>
<gretl-output>
? logit y const x1
Perfect prediction obtained: no MLE exists
? err = $error
Generated scalar err = 33
err = 33 (The convergence criterion was not met)
</gretl-output>
Allin Cottrell
7:03 a.m.
Hi Allin, actually it seems to work now after updating gretl frequently
since the issue occurred last time. The error number is 36.
Best,
Artur
Am 31.08.2013 05:00, schrieb Cottrell, Allin:
On Thu, Aug 22, 2013 at 4:56 AM, Artur Tarassow
>
> after estimating a LOGIT model I obtain the following message:
>
> "Note: armeu == 0 predicts failure perfectly
> 714 observations not used
> Not a Number in calculation"
>
> I used the command "catch logit ..." to control for any error. I am
> wondered why the $error flag is still zero despite the message. Should
> this not result in a non-zero error value?
Artur, could you please send (offlist if the data are big) your data and
script?
In a simple case of perfect prediction I'm getting a non-zero $error
OK (example below) but apparently the case you're looking at is
more complicated.
<hansl>
nulldata 100
series x1 = normal()
series ndx = 1.5 + 2*x1
series y = ndx > 0
catch logit y 0 x1
err = $error
if err
printf "err = %d (%s)\n", err, errmsg(err)
else
print "no error"
endif
</hansl>
<gretl-output>
? logit y const x1
Perfect prediction obtained: no MLE exists
? err = $error
Generated scalar err = 33
err = 33 (The convergence criterion was not met)
</gretl-output>
Allin Cottrell
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users
--
For global instant messaging use the free and transparent Jabber chat:
t.artur(a)ubuntu-jabber.de
Avoid Facebook and join me on Diaspora: https://despora.de/i/9fba3608d45a
If you want to use encrypted emailing, here is my public PGP key:
-----BEGIN PGP PUBLIC KEY BLOCK-----
Version: GnuPG v1.4.12 (GNU/Linux)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=tQPP
-----END PGP PUBLIC KEY BLOCK-----
4107
days inactive
4122
days old
2 comments
3 participants
participants (3)
-
Artur T. -
Artur Tarassow
-
Cottrell, Allin