xtreg command

[GUIRA Asmo]

good evening to all,
how to use the xtreg command. I tried with the following formula: xtreg logrend_cereale logU logDose_Bphosphate Grant, re. But this message appears:

error . . . . . . . . . . . . . . . . . . . . . . . . Return code 459
something that should be true of your data is not;
data have changed since estimation;
This is the generic form of this message; more likely, you
will see messages such as "y must be between 0 and 1" or
"x not positive". You have attempted to do something that,
given your data, does not make sense.

Can someone help me to execute my command. thanks

[Jared Greathouse]

Watch this please.

[Carlo Lazzaro]

GUIRA:
at a very first glance, your code looks legal.
Is this exactly what you typed?
Is your regressand continuous?
Have you -xtset- your dataset before going -xtreg,re-?
Please note that without further details from you side, guess-work rules.

[Jared Greathouse]

Is this exactly what you typed?

I'm convinced that it can't be the exact code. I'd almost bet my next paycheck on it. Why?.


I considered the idea that the data weren't xtset, but Stata has a specific code for that. The regressand being continuous shouldn't matter, since OLS doesn't care at all about if its predictors or outcomes continuous or discrete or whatever. So at the very lest, the error isn't shown in full context. The code is as legal as saying "amo mia madre" on Mother's Day.

[GUIRA Asmo]

yes Carlo I have continuous and variable regressors.
Jared, what is your problem
thanks

[William Lisowski]

GUIRA Asmo -

What you show in post #1 is the output of

help rc 459

which is displayed by clicking on the r(459) in the Stata Results window.

But there should be an error message displayed in red in your Stata Results window on the line preceding the r(459) return code. That is the error mesage that was "more likely" to be something informative.

Can you tell us what that error message was?

[Carlo Lazzaro]

GUIRA:
as an aside to previous helpful insights, the only Jared's problem I see is his perfect Italian 😀.
What strikes me is the fact that Stata did not report other, more constructive messages (as it is often the case).