Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: gllamm


From   "Stella Capuano" <[email protected]>
To   [email protected]
Subject   Re: st: gllamm
Date   Fri, 11 Apr 2008 09:48:46 +0200 (CEST)

I am sorry, but I have always the same error message, so it was not  a
problem of dummy variables.
This time I have typed
xi: gllamm alternative i.age i.rate , i(individual) link(mlogit)
expanded(individual choice o)
as suggested, but I have received again the same error message, namely:

could not calculate numerical derivatives
missing values encountered
(error occurred in ML computation)
(use trace option and check correctness of initial model)

Can anyone suggest me what to do?
Many thanks,
Stella
--
Stella Capuano
c/o Collegio Carlo Alberto
Via Real Collegio, 30
10024
Moncalieri (TO)

>
>
> -------------------------- Messaggio originale ---------------------------
> Oggetto: Re: st: gllamm
> Da:      "Hind Sbihi" <[email protected]>
> Data:    Gio, 10 Aprile 2008, 7:27 pm
> A:       [email protected]
> --------------------------------------------------------------------------
>
>
> Hi Stella
>
> you probably want to add the xi statement before your command
>
> xi: gllamm alternative i.age i.rate , i(individual) link(mlogit)
> expanded(individual choice o)
> where age and rate are your categorical variables
> Stata will take care of creating dummy variables for you
>
> HTH
>
> Hind
>
> -----Original Message-----
>
>> Date: Thu Apr 10 10:16:37 PDT 2008
>> From: "Stella Capuano" <[email protected]>
>> Subject: st: gllamm
>> To: [email protected]
>>
>> Dear Statalisters,
>> I have problems with stata command gllamm: it says that the likelihood
>> cannot be computed because missing values were encountered during the
>> computation. I don't understand what it means (my data do not have
>> missing
>> values).
>> I have, hopefully correctly, reshaped the data in this way
>> individual alternative choice
>> 1                1            0
>> 1                2            0
>> 1                3            1
>> 1                4            0
>> etc...for each individual. The command I type is:
>> gllamm alternative age1 age2 age3 age4 un_rate_1 un_rate_2 un_rate_3
>> un_rate4, i(individual) link(mlogit) expanded(individual choice o)
>> where age1, age2, age3, age4 are age dummies (each for one age category)
>> and un_rate_1, un_rate_2, un_rate_3, un_rate_4 are regional unemployment
>> rates (indeed the alternatives are regions.
>> Honestly, I haven't understood properly what to specify in option i(),
>> however I always get the same error message.
>> Please, can anyone give me a hand?
>> Thanks a lot,
>> Stella
>> --
>> Stella Capuano
>> c/o Collegio Carlo Alberto
>> Via Real Collegio, 30
>> 10024
>> Moncalieri (TO)
>>
>>
>> *
>> *   For searches and help try:
>> *   http://www.stata.com/support/faqs/res/findit.html
>> *   http://www.stata.com/support/statalist/faq
>> *   http://www.ats.ucla.edu/stat/stata/
>
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>
>

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index