El diseño muestral es el que se logró armar considerando los diseños de cada paÃs Finalmente se trabaja con un diseño equivalente a 2 etapas, primera donde las psu son las escuelas, el pais es la variable de estratficacióny se usan como pesos muestrales los que se consideraron en Uruguay (ver diseño de Uruguay y para POA se creó un nuevo vector de peso usando como variables de ajuste distribucion por sexo y por tipo de escuela)
names(disenio_urubra$variables) [1] “id” “pais” “ficha”
[4] “eta” “tipoesc” “sexoinv”
[7] “weight” “weight.rec” “numesc”
[10] “numer_esc” “idade” “socioecon4cat”
[13] “socioecon3cat” “escolmae” “escolmae13cat”
[16] “escolmaerecat23cat” “freqescov” “freqescovacat”
[19] “usofio” “freqfio” “usocreme”
[22] “idadcreme” “visidentcatonde” “visiquando”
[25] “fluorprof” “idadefluor” “isg.”
[28] “isg45” “isg20” “cposoms”
[31] “cpodoms” “prevoms” “cposbere”
[34] “cpodbere” “prevbere” “cposicdas”
[37] “cpodicdas” “previcdas”
#
# load('~/Dropbox/odontologia/maestria_anunziatta/BancoUnidoBrasUru/BRASURU.RData')
load("C:/Users/usuario/Dropbox/odontologia/maestria_anunziatta/BancoUnidoBrasUru/BRASURU.RData")
library(survey)
## Attaching package: 'survey'
## The following object(s) are masked from 'package:graphics':
##
## dotchart
library(car)
## Loading required package: MASS
## Loading required package: nnet
# 10 de octubre 2013
modelo0.bin <- svyglm(prevoms ~ pais, disenio_urubra, family = quasibinomial())
summary(modelo0.bin)
##
## Call:
## svyglm(formula = prevoms ~ pais, disenio_urubra, family = quasibinomial())
##
## Survey design:
## svydesign(id = ~numer_esc, strata = ~pais, weights = ~round(weight.rec,
## 1), data = brasuru, nest = TRUE)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.2185 0.0952 2.30 0.024 *
## paisUru 0.2484 0.1420 1.75 0.084 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for quasibinomial family taken to be 1)
##
## Number of Fisher Scoring iterations: 4
confint(modelo0.bin)
## 2.5 % 97.5 %
## (Intercept) 0.03195 0.4050
## paisUru -0.02999 0.5268
exp(modelo0.bin$coefficients)
## (Intercept) paisUru
## 1.244 1.282
modelo1.bin <- svyglm(prevoms ~ sexoinv + pais, disenio_urubra, family = quasibinomial())
summary(modelo1.bin)
##
## Call:
## svyglm(formula = prevoms ~ sexoinv + pais, disenio_urubra, family = quasibinomial())
##
## Survey design:
## svydesign(id = ~numer_esc, strata = ~pais, weights = ~round(weight.rec,
## 1), data = brasuru, nest = TRUE)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.1745 0.1130 1.54 0.127
## sexoinv2-F 0.0897 0.1277 0.70 0.485
## paisUru 0.2494 0.1422 1.75 0.083 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for quasibinomial family taken to be 1)
##
## Number of Fisher Scoring iterations: 4
confint(modelo1.bin)
## 2.5 % 97.5 %
## (Intercept) -0.04707 0.3960
## sexoinv2-F -0.16064 0.3400
## paisUru -0.02925 0.5281
exp(modelo1.bin$coefficients)
## (Intercept) sexoinv2-F paisUru
## 1.191 1.094 1.283
modelo2.bin <- svyglm(prevoms ~ socioecon4cat + pais, disenio_urubra, family = quasibinomial())
summary(modelo2.bin)
##
## Call:
## svyglm(formula = prevoms ~ socioecon4cat + pais, disenio_urubra,
## family = quasibinomial())
##
## Survey design:
## svydesign(id = ~numer_esc, strata = ~pais, weights = ~round(weight.rec,
## 1), data = brasuru, nest = TRUE)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.683 0.185 -3.70 0.00041 ***
## socioecon4cat2-medio-alto 0.634 0.222 2.86 0.00549 **
## socioecon4cat3-medio-bajo 1.109 0.192 5.78 1.5e-07 ***
## socioecon4cat4-bajo 1.454 0.228 6.38 1.2e-08 ***
## paisUru 0.395 0.124 3.18 0.00209 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for quasibinomial family taken to be 1)
##
## Number of Fisher Scoring iterations: 4
confint(modelo2.bin)
## 2.5 % 97.5 %
## (Intercept) -1.0453 -0.3211
## socioecon4cat2-medio-alto 0.1990 1.0681
## socioecon4cat3-medio-bajo 0.7333 1.4855
## socioecon4cat4-bajo 1.0075 1.9005
## paisUru 0.1520 0.6388
exp(modelo2.bin$coefficients)
## (Intercept) socioecon4cat2-medio-alto
## 0.505 1.884
## socioecon4cat3-medio-bajo socioecon4cat4-bajo
## 3.033 4.280
## paisUru
## 1.485
modelo3.bin <- svyglm(prevoms ~ socioecon3cat + pais, disenio_urubra, family = quasibinomial())
summary(modelo3.bin)
##
## Call:
## svyglm(formula = prevoms ~ socioecon3cat + pais, disenio_urubra,
## family = quasibinomial())
##
## Survey design:
## svydesign(id = ~numer_esc, strata = ~pais, weights = ~round(weight.rec,
## 1), data = brasuru, nest = TRUE)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.565 0.156 -3.62 0.00052 ***
## socioecon3cat2-medio 0.828 0.156 5.30 1.0e-06 ***
## socioecon3cat3-bajo 1.332 0.193 6.90 1.2e-09 ***
## paisUru 0.402 0.129 3.11 0.00258 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for quasibinomial family taken to be 1)
##
## Number of Fisher Scoring iterations: 4
confint(modelo3.bin)
## 2.5 % 97.5 %
## (Intercept) -0.8716 -0.2593
## socioecon3cat2-medio 0.5218 1.1340
## socioecon3cat3-bajo 0.9536 1.7103
## paisUru 0.1489 0.6545
exp(modelo3.bin$coefficients)
## (Intercept) socioecon3cat2-medio socioecon3cat3-bajo
## 0.5681 2.2885 3.7884
## paisUru
## 1.4944
modelo4.bin <- svyglm(prevoms ~ escolmaerecat23cat + pais, disenio_urubra, family = quasibinomial())
summary(modelo4.bin)
##
## Call:
## svyglm(formula = prevoms ~ escolmaerecat23cat + pais, disenio_urubra,
## family = quasibinomial())
##
## Survey design:
## svydesign(id = ~numer_esc, strata = ~pais, weights = ~round(weight.rec,
## 1), data = brasuru, nest = TRUE)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.526 0.144 -3.65 0.00047
## escolmaerecat23cat2-high school 0.560 0.153 3.65 0.00047
## escolmaerecat23cat3-elementary school 1.140 0.167 6.83 1.7e-09
## paisUru 0.466 0.119 3.92 0.00019
##
## (Intercept) ***
## escolmaerecat23cat2-high school ***
## escolmaerecat23cat3-elementary school ***
## paisUru ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for quasibinomial family taken to be 1.002)
##
## Number of Fisher Scoring iterations: 4
confint(modelo4.bin)
## 2.5 % 97.5 %
## (Intercept) -0.8085 -0.2436
## escolmaerecat23cat2-high school 0.2595 0.8607
## escolmaerecat23cat3-elementary school 0.8128 1.4670
## paisUru 0.2331 0.6983
exp(modelo4.bin$coefficients)
## (Intercept)
## 0.5909
## escolmaerecat23cat2-high school
## 1.7508
## escolmaerecat23cat3-elementary school
## 3.1264
## paisUru
## 1.5932
modelo5.bin <- svyglm(prevoms ~ escolmae13cat + pais, disenio_urubra, family = quasibinomial())
summary(modelo5.bin)
##
## Call:
## svyglm(formula = prevoms ~ escolmae13cat + pais, disenio_urubra,
## family = quasibinomial())
##
## Survey design:
## svydesign(id = ~numer_esc, strata = ~pais, weights = ~round(weight.rec,
## 1), data = brasuru, nest = TRUE)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.686 0.185 -3.70 0.0004 ***
## escolmae13cat2-high school 0.596 0.238 2.50 0.0146 *
## escolmae13cat3-Elementary School 1.233 0.179 6.88 1.3e-09 ***
## paisUru 0.306 0.121 2.52 0.0137 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for quasibinomial family taken to be 1.003)
##
## Number of Fisher Scoring iterations: 4
confint(modelo5.bin)
## 2.5 % 97.5 %
## (Intercept) -1.04872 -0.3226
## escolmae13cat2-high school 0.12852 1.0632
## escolmae13cat3-Elementary School 0.88200 1.5843
## paisUru 0.06835 0.5446
exp(modelo5.bin$coefficients)
## (Intercept) escolmae13cat2-high school
## 0.5038 1.8146
## escolmae13cat3-Elementary School paisUru
## 3.4320 1.3586
modelo6.bin <- svyglm(prevoms ~ freqescovacat + pais, disenio_urubra, family = quasibinomial())
summary(modelo6.bin)
##
## Call:
## svyglm(formula = prevoms ~ freqescovacat + pais, disenio_urubra,
## family = quasibinomial())
##
## Survey design:
## svydesign(id = ~numer_esc, strata = ~pais, weights = ~round(weight.rec,
## 1), data = brasuru, nest = TRUE)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.607 0.126 4.81 7.1e-06 ***
## freqescovacat2-veces al día -0.396 0.127 -3.11 0.00263 **
## freqescovacat3-veces al día -0.615 0.152 -4.06 0.00012 ***
## paisUru 0.297 0.144 2.06 0.04259 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for quasibinomial family taken to be 1.001)
##
## Number of Fisher Scoring iterations: 4
confint(modelo6.bin)
## 2.5 % 97.5 %
## (Intercept) 0.35964 0.8537
## freqescovacat2-veces al día -0.64513 -0.1461
## freqescovacat3-veces al día -0.91192 -0.3180
## paisUru 0.01463 0.5798
exp(modelo6.bin$coefficients)
## (Intercept) freqescovacat2-veces al día
## 1.8343 0.6733
## freqescovacat3-veces al día paisUru
## 0.5407 1.3461
modelo7.bin <- svyglm(prevoms ~ usocreme + pais, disenio_urubra, family = quasibinomial())
summary(modelo7.bin)
##
## Call:
## svyglm(formula = prevoms ~ usocreme + pais, disenio_urubra, family = quasibinomial())
##
## Survey design:
## svydesign(id = ~numer_esc, strata = ~pais, weights = ~round(weight.rec,
## 1), data = brasuru, nest = TRUE)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.2086 0.0941 2.22 0.030 *
## usocreme2-No 0.5833 0.3843 1.52 0.133
## paisUru 0.2455 0.1421 1.73 0.088 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for quasibinomial family taken to be 1.002)
##
## Number of Fisher Scoring iterations: 4
confint(modelo7.bin)
## 2.5 % 97.5 %
## (Intercept) 0.02415 0.3931
## usocreme2-No -0.16986 1.3365
## paisUru -0.03304 0.5241
exp(modelo7.bin$coefficients)
## (Intercept) usocreme2-No paisUru
## 1.232 1.792 1.278
modelo8.bin <- svyglm(prevoms ~ visidentcatonde + pais, disenio_urubra, family = quasibinomial())
summary(modelo8.bin)
##
## Call:
## svyglm(formula = prevoms ~ visidentcatonde + pais, disenio_urubra,
## family = quasibinomial())
##
## Survey design:
## svydesign(id = ~numer_esc, strata = ~pais, weights = ~round(weight.rec,
## 1), data = brasuru, nest = TRUE)
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) -0.1521 0.0884 -1.72
## visidentcatonde2-Publico 0.8539 0.1107 7.71
## visidentcatonde3-Nunca fue al dentista 0.5815 0.1358 4.28
## paisUru 0.3175 0.1245 2.55
## Pr(>|t|)
## (Intercept) 0.089 .
## visidentcatonde2-Publico 3.4e-11 ***
## visidentcatonde3-Nunca fue al dentista 5.2e-05 ***
## paisUru 0.013 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for quasibinomial family taken to be 0.9946)
##
## Number of Fisher Scoring iterations: 4
confint(modelo8.bin)
## 2.5 % 97.5 %
## (Intercept) -0.32530 0.02119
## visidentcatonde2-Publico 0.63691 1.07087
## visidentcatonde3-Nunca fue al dentista 0.31525 0.84773
## paisUru 0.07354 0.56153
exp(modelo8.bin$coefficients)
## (Intercept)
## 0.8589
## visidentcatonde2-Publico
## 2.3488
## visidentcatonde3-Nunca fue al dentista
## 1.7887
## paisUru
## 1.3737
modelo9.bin <- svyglm(prevoms ~ visiquando + pais, disenio_urubra, family = quasibinomial())
summary(modelo9.bin)
##
## Call:
## svyglm(formula = prevoms ~ visiquando + pais, disenio_urubra,
## family = quasibinomial())
##
## Survey design:
## svydesign(id = ~numer_esc, strata = ~pais, weights = ~round(weight.rec,
## 1), data = brasuru, nest = TRUE)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.1388 0.1060 1.31 0.194
## visiquando2- más de 2 años 0.0584 0.1578 0.37 0.713
## visiquando3- nunca fue 0.3275 0.1306 2.51 0.014 *
## paisUru 0.2713 0.1454 1.87 0.066 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for quasibinomial family taken to be 0.9979)
##
## Number of Fisher Scoring iterations: 4
confint(modelo9.bin)
## 2.5 % 97.5 %
## (Intercept) -0.06896 0.3466
## visiquando2- más de 2 años -0.25092 0.3676
## visiquando3- nunca fue 0.07144 0.5835
## paisUru -0.01360 0.5562
exp(modelo9.bin$coefficients)
## (Intercept) visiquando2- más de 2 años
## 1.149 1.060
## visiquando3- nunca fue paisUru
## 1.387 1.312
modelo10.bin <- svyglm(prevoms ~ fluorprof + pais, disenio_urubra, family = quasibinomial())
summary(modelo10.bin)
##
## Call:
## svyglm(formula = prevoms ~ fluorprof + pais, disenio_urubra,
## family = quasibinomial())
##
## Survey design:
## svydesign(id = ~numer_esc, strata = ~pais, weights = ~round(weight.rec,
## 1), data = brasuru, nest = TRUE)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.1847 0.1020 1.81 0.074 .
## fluorprof2-No 0.0965 0.1234 0.78 0.436
## paisUru 0.2179 0.1445 1.51 0.136
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for quasibinomial family taken to be 0.9991)
##
## Number of Fisher Scoring iterations: 4
confint(modelo10.bin)
## 2.5 % 97.5 %
## (Intercept) -0.01522 0.3846
## fluorprof2-No -0.14527 0.3383
## paisUru -0.06529 0.5012
exp(modelo10.bin$coefficients)
## (Intercept) fluorprof2-No paisUru
## 1.203 1.101 1.244
modelo11.bin <- svyglm(prevoms ~ isg20 + pais, disenio_urubra, family = quasibinomial())
summary(modelo11.bin)
##
## Call:
## svyglm(formula = prevoms ~ isg20 + pais, disenio_urubra, family = quasibinomial())
##
## Survey design:
## svydesign(id = ~numer_esc, strata = ~pais, weights = ~round(weight.rec,
## 1), data = brasuru, nest = TRUE)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.0299 0.1780 -0.17 0.8670
## isg202- 20 a 60 0.0505 0.1689 0.30 0.7659
## isg203- >=60 0.7062 0.1643 4.30 4.9e-05 ***
## paisUru 0.4274 0.1382 3.09 0.0028 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for quasibinomial family taken to be 1.001)
##
## Number of Fisher Scoring iterations: 4
confint(modelo11.bin)
## 2.5 % 97.5 %
## (Intercept) -0.3789 0.3190
## isg202- 20 a 60 -0.2806 0.3816
## isg203- >=60 0.3843 1.0282
## paisUru 0.1564 0.6983
exp(modelo11.bin$coefficients)
## (Intercept) isg202- 20 a 60 isg203- >=60 paisUru
## 0.9705 1.0518 2.0263 1.5332
modelo12.bin <- svyglm(prevoms ~ isg45 + pais, disenio_urubra, family = quasibinomial())
summary(modelo12.bin)
##
## Call:
## svyglm(formula = prevoms ~ isg45 + pais, disenio_urubra, family = quasibinomial())
##
## Survey design:
## svydesign(id = ~numer_esc, strata = ~pais, weights = ~round(weight.rec,
## 1), data = brasuru, nest = TRUE)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.142 0.117 -1.21 0.2285
## isg452- 45 a 60 0.338 0.131 2.59 0.0114 *
## isg453- >=60 0.801 0.139 5.75 1.7e-07 ***
## paisUru 0.514 0.141 3.64 0.0005 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for quasibinomial family taken to be 1.002)
##
## Number of Fisher Scoring iterations: 4
confint(modelo12.bin)
## 2.5 % 97.5 %
## (Intercept) -0.37106 0.08724
## isg452- 45 a 60 0.08246 0.59422
## isg453- >=60 0.52774 1.07395
## paisUru 0.23667 0.79051
exp(modelo12.bin$coefficients)
## (Intercept) isg452- 45 a 60 isg453- >=60 paisUru
## 0.8677 1.4026 2.2274 1.6713