Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: collinearity/non-convergence problem with -asclogit- command


From   Cielo Magno <cielomagno@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: collinearity/non-convergence problem with -asclogit- command
Date   Mon, 12 Oct 2009 21:12:05 -0400

Hi Jade!  I have 18,652 observation and 1,841 cases.

Cielo

On Mon, Oct 12, 2009 at 8:46 PM, Jade Redoblado
<jade.redoblado@gmail.com> wrote:
> How many observations do you have, Cielo?
>
> On 10/13/09, Cielo Magno <cielomagno@gmail.com> wrote:
>> Hello everyone,
>>
>> I am hoping someone will be able to help me with my problem. I am new
>> with Stata and I am trying to run the -asclogit- command. The model
>> always results in non convergence because of collinear variables.
>>
>> I want to start with a simple model, just 1 alternative-specific
>> variable and 1 case-specific variable but I can’t even get pass it.
>> This is the command I am using:
>>
>> . asclogit choice price2, casevars(age) case (id) alternative (alter)
>> iter(5)
>>
>> This is how my data looks like.  There are 11 products, my
>> alternative-specific variables are the price of the product and the
>> amount of money they spent on advertising every month.
>>
>> I tried to replace price2 with the advertising variable and the result
>> is still the same.  I also tried creating a dichotomous variable (by
>> transforming my advertising variable into a dichotomous yes/no
>> variable) and using it as the alternative-specific variable but the
>> result is the same – non convergence.
>>
>>
>> +-----------------------------------------------------+
>>      | choice         price2   age   id       alter           total_ads |
>>      |-----------------------------------------------------|
>>   1. |      1         110     83   33         product1    15488033 |
>>   2. |      0         92      83   33         product2    11891267 |
>>   3. |      0                 101     83   33         product3    0 |
>>   4. |      0         77      83   33         product4    0 |
>>   5. |      0         82      83   33         product5        49783.33 |
>>   6. |      0         104     83   33       product6          27916.67 |
>>   7. |      0         122     83   33         product7    21012.50 |
>>   8. |      0         168     83   33         product8   166.67 |
>>   9. |      0                          107            83   33         product9    0 |
>>  10. |     0           58     83   33         product10  0 |
>>  11. |     0          153     83   33         product11  0 |
>>      |-----------------------------------------------------|
>>  12. |      1         110     61   37         product1    15488033 |
>>  13. |      0         92      61   37         product2    11891267 |
>>  14. |      0         101     61   37         product3    0 |
>>  15. |      0         77      61   37       product4    0 |
>>  16. |      0         82      61   37         product5        49783.33 |
>>  17. |      0         104     61   37       product6   27916.67 |
>>  18. |      0         122     61   37         product7    21012.5 |
>>  19. |      0         168     61   37         product8   166.67 |
>>  20. |      0         107     61   37         product9    0 |
>>  21. |      0         58      61   37         product10  0 |
>>  22. |      0         153     61   37         product11  0 |
>>      +-----------------------------------------------------+
>>
>>
>> I can’t figure out/find a solution to my problem.  I am using Stata/IC
>> 11.0 and it is updated.  Any help will be greatly appreciated.
>> Thank you very much.
>>
>>
>> Cielo Magno
>> Graduate student
>> Law, Policy & Society
>> Northeatern University
>>
>> *
>> *   For searches and help try:
>> *   http://www.stata.com/help.cgi?search
>> *   http://www.stata.com/support/statalist/faq
>> *   http://www.ats.ucla.edu/stat/stata/
>>
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index