R help - Apr 2014 - Survey

Dear R-Users,

I was using survey for the past years and now I am experiencing some
problems with scripts that was working in the past.

We are working with big data bases so I can't put all variables that I will
use in the svydesign.


Script working:
> data(api)
> dclus1<-svydesign(id=apiclus1$dnum, weights=apiclus1$pw,
fpc=apiclus1$fpc)
> svyby(apiclus1$api99,apiclus1$stype, dclus1, svymean)
  by       V1       se
E  E 607.7917 22.81660
H  H 595.7143 41.76400
M  M 608.6000 32.56064
> svyby(apiclus1$api99,~apiclus1$stype, dclus1, svymean)
  apiclus1$stype       V1       se
E              E 607.7917 22.81660
H              H 595.7143 41.76400
M              M 608.6000 32.56064
> dclus1<-svydesign(id=~dnum, weights=~pw, data=apiclus1, fpc=~fpc)
> svyby(~api99, ~stype, dclus1, svymean)
  stype    api99 se.api99
E     E 607.7917 22.81660
H     H 595.7143 41.76400
M     M 608.6000 32.56064
> sessionInfo()
R version 2.12.1 (2010-12-16)
Platform: x86_64-pc-mingw32/x64 (64-bit)

locale:
[1] LC_COLLATE=Portuguese_Brazil.1252  LC_CTYPE=Portuguese_Brazil.1252
 LC_MONETARY=Portuguese_Brazil.1252
[4] LC_NUMERIC=C                       LC_TIME=Portuguese_Brazil.1252

attached base packages:
[1] grDevices datasets  splines   graphics  stats     tcltk     utils
methods   base

other attached packages:
[1] gdata_2.8.2     survey_3.26     foreign_0.8-42  SOAR_0.99-8
svSocket_0.9-51 TinnR_1.0.3     R2HTML_2.2
[8] Hmisc_3.8-3     survival_2.36-2

loaded via a namespace (and not attached):
[1] cluster_1.14.1  grid_2.12.1     gtools_2.6.2    lattice_0.19-33
svMisc_0.9-63   tools_2.12.1



script not working:
> data(api)
>
> dclus1<-svydesign(id=apiclus1$dnum, weights=apiclus1$pw,
fpc=apiclus1$fpc)
> svyby(apiclus1$api99,apiclus1$stype, dclus1, svymean)
Erro em svyby.default(apiclus1$api99, apiclus1$stype, dclus1, svymean) :
  objeto 'byfactor' não encontrado
> svyby(apiclus1$api99,~apiclus1$stype, dclus1, svymean)
Erro em svyby.default(apiclus1$api99, ~apiclus1$stype, dclus1, svymean) :
  objeto 'byfactor' não encontrado
>
> dclus1<-svydesign(id=~dnum, weights=~pw, data=apiclus1, fpc=~fpc)
> svyby(~api99, ~stype, dclus1, svymean)
  stype    api99       se
E     E 607.7917 22.81660
H     H 595.7143 41.76400
M     M 608.6000 32.56064
> sessionInfo()
R version 3.0.3 (2014-03-06)
Platform: x86_64-w64-mingw32/x64 (64-bit)

locale:
[1] LC_COLLATE=Portuguese_Brazil.1252  LC_CTYPE=Portuguese_Brazil.1252
 LC_MONETARY=Portuguese_Brazil.1252 LC_NUMERIC=C
LC_TIME=Portuguese_Brazil.1252

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base

other attached packages:
[1] survey_3.29-5

loaded via a namespace (and not attached):
[1] tools_3.0.3
>
	[[alternative HTML version deleted]]

On Thu, Apr 3, 2014 at 2:37 AM, Leandro Marino <
leandromarino@leandromarino.com.br> wrote:
> Dear R-Users,
>
> I was using survey for the past years and now I am experiencing some
> problems with scripts that was working in the past.
>
> We are working with big data bases so I can't put all variables that I
will
> use in the svydesign.
>
This was never supposed to work.

The variables shouldn't take up any more room in the survey design object
than they do anywhere else, but in any case the right solution when you
have enough memory for the variables in a given analysis but not for all
the variables in your dataset is to use the database-backed designs and put
the data in something like SQLite.

  -thomas

-- 
Thomas Lumley
Professor of Biostatistics
University of Auckland

	[[alternative HTML version deleted]]