Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

Re: st: _rmcoll issues


From   Stas Kolenikov <skolenik@gmail.com>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: _rmcoll issues
Date   Tue, 10 Dec 2013 22:43:50 -0500

That's still not the right answer to the problem. I ended up creating
the interaction of the two with seven levels, and using that in the
regression, although I would rather have the main effects.

-- Stas Kolenikov, PhD, PStat (ASA, SSC)
-- Senior Survey Statistician, Abt SRBI
-- Opinions stated in this email are mine only, and do not reflect the
position of my employer
-- http://stas.kolenikov.name



On Tue, Dec 10, 2013 at 10:39 PM, Richard Williams
<richardwilliams.ndu@gmail.com> wrote:
> At 05:31 PM 12/10/2013, Stas Kolenikov wrote:
>>
>> I have the following cross-tab of two variables:
>>
>> . tab pd2usmex years_in_us
>>
>>  PD2. What |
>>    country |
>>   were you |                 years_in_us
>>   born in? |         1          2          3          4 |     Total
>> -----------+--------------------------------------------+----------
>>          1 |       240          0          0          0 |       240
>>          2 |         0        103        451        378 |       932
>>          9 |         0         33         99        123 |       255
>> -----------+--------------------------------------------+----------
>>      Total |       240        136        550        501 |     1,427
>>
>> For whatever reason, _rmcoll senses that something is fishy between
>> the two variables, but decides to drop the last category of the second
>> variable, rather than the first one on which these two variables
>> logically overlap.
>>
>> . _rmcoll ib1.pd2usmex ib1.years_in_us
>> note: 4.years_in_us omitted because of collinearity
>>
>> I think this is a bit odd.
>
>
> I think it just goes with the highest code. Try running this (drop the fws
> if you don't need them):
>
> preserve
> recode years_in_us (3 = 5)
> _rmcoll ib1.pd2usmex ib1.years_in_us [fw = freq]
> recode years_in_us (2 = 6)
> _rmcoll ib1.pd2usmex ib1.years_in_us [fw = freq]
> restore
> preserve
> recode years_in_us (1 = 5)
> recode years_in_us (2 = 1)
> _rmcoll ib1.pd2usmex ib1.years_in_us [fw = freq]
> restore
>
> The highest value always gets dropped.
>
>
>
>> -- Stas Kolenikov, PhD, PStat (ASA, SSC)
>> -- Senior Survey Statistician, Abt SRBI
>> -- Opinions stated in this email are mine only, and do not reflect the
>> position of my employer
>> -- http://stas.kolenikov.name
>> *
>> *   For searches and help try:
>> *   http://www.stata.com/help.cgi?search
>> *   http://www.stata.com/support/faqs/resources/statalist-faq/
>> *   http://www.ats.ucla.edu/stat/stata/
>
>
> -------------------------------------------
> Richard Williams, Notre Dame Dept of Sociology
> OFFICE: (574)631-6668, (574)631-6463
> HOME:   (574)289-5227
> EMAIL:  Richard.A.Williams.5@ND.Edu
> WWW:    http://www.nd.edu/~rwilliam
>
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index