[R] svytable: How do i create a table informing a third variable?

[David Winsemius]

> On Sep 2, 2016, at 6:08 PM, Juan Ceccarelli Arias <jfca283 at gmail.com> wrote:
> 
> Thanks a lot. Your code does the trick.
> One last question:
> The tabulate produced is showing every cross in just one column.
> I mean, it presents the region by order and sex=1, and then again the
> region but by sex==2.
> Can i list or present as this:
>             sex1         sex2
> region1  323.      3434..
> ...
> regionN 123..  432..
> 
> and ignoring the remaining info (standar errors or se in this case)?
> Again, thanks Anthony. Really.
> 
(Anthony's probably asleep.)

This doesn't ignore the se's but that could be easily done by omitting that column from the data argument:

From the examples on the help page for svymean:

> svyby( ~ mobility , ~ stype + comp.imp , dclus1 , svymean )
      stype comp.imp mobility        se
E.No      E       No 19.71875  1.347583
H.No      H       No 13.14286  0.740017
M.No      M       No 14.81818  2.960618
E.Yes     E      Yes 17.28571  1.536158
H.Yes     H      Yes 35.14286 16.570001
M.Yes     M      Yes 13.71429  2.628573

apimeans1 <- svyby( ~ mobility , ~ stype + comp.imp , dclus1 , svymean )

> reshape(apimeans1, idvar='stype', direction="wide", timevar="comp.imp")
     stype mobility.No    se.No mobility.Yes    se.Yes
E.No     E    19.71875 1.347583     17.28571  1.536158
H.No     H    13.14286 0.740017     35.14286 16.570001
M.No     M    14.81818 2.960618     13.71429  2.628573

-- 
David.

> 
> 
> 
> 
> On Fri, Sep 2, 2016 at 8:24 PM, Anthony Damico <ajdamico at gmail.com> wrote:
> 
>> # mean
>> svymean( ~ income_variable , NN )
>> svyby( ~ income_variable , ~ age + sex , NN , svymean )
>> 
>> # median
>> svyquantile( ~ income_variable , NN )
>> svyby( ~ income_variable , ~ age + sex , NN , svyquantile , 0.5 )
>> 
>> 
>> 
>> 
>> On Fri, Sep 2, 2016 at 3:04 PM, Juan Ceccarelli Arias <jfca283 at gmail.com>
>> wrote:
>> 
>>> Hello
>>> Im analyzing a survey and i need to obtain some statistics per groups.
>>> Im able to create a table with sex and age. However, if i want to know how
>>> much income earns the population by sex and age, i can't.
>>> Im loading the dataset as describe the line below
>>> NN <- svydesign(ids = ~1, data = encuesta, weights = fact)
>>> Some simple table i can create
>>> table(svytable(~age+sex,design=NN))
>>> But im not able to handle the same tabulate referencing a income variable,
>>> in this case, wage.
>>> Can you help me?
>>> Thanks for your replies and time.
>>> 
>>>        [[alternative HTML version deleted]]
>>> 
>>> ______________________________________________
>>> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
>>> https://stat.ethz.ch/mailman/listinfo/r-help
>>> PLEASE do read the posting guide http://www.R-project.org/posti
>>> ng-guide.html
>>> and provide commented, minimal, self-contained, reproducible code.
>>> 
>> 
>> 
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.