Aca se analiza como se distribuye la erosion para las piezas 17 15 21 acumulando para cada pieza la cara V,P,I
library(survey)
## Attaching package: 'survey'
##
## The following object(s) are masked from 'package:graphics':
##
## dotchart
options(OutDec = ",")
library(car)
## Loading required package: MASS Loading required package: nnet
load("~/Dropbox/odontologia/maestria licet/octubre 2013/datos_licet_16102013.RData")
erosion <- read.csv("erosion.csv")
diseniopost1$variables <- cbind(diseniopost1$variables, erosion[, c(2:29)])
names(diseniopost1$variables[, 456:483])
## [1] "Eros17" "Eros16" "Eros15" "Eros14" "Eros13" "Eros12" "Eros11"
## [8] "Eros21" "Eros22" "Eros23" "Eros24" "Eros25" "Eros26" "Eros27"
## [15] "Eros37" "Eros36" "Eros35" "Eros34" "Eros33" "Eros32" "Eros31"
## [22] "Eros41" "Eros42" "Eros43" "Eros44" "Eros45" "Eros46" "Eros47"
Recodifica y pasa a Factores
diseniopost1$variables$Eros17 <- as.factor(diseniopost1$variables$Eros17)
diseniopost1$variables$Eros16 <- as.factor(diseniopost1$variables$Eros16)
diseniopost1$variables$Eros15 <- as.factor(diseniopost1$variables$Eros15)
diseniopost1$variables$Eros14 <- as.factor(diseniopost1$variables$Eros14)
diseniopost1$variables$Eros13 <- as.factor(diseniopost1$variables$Eros13)
diseniopost1$variables$Eros12 <- as.factor(diseniopost1$variables$Eros12)
diseniopost1$variables$Eros11 <- as.factor(diseniopost1$variables$Eros11)
diseniopost1$variables$Eros21 <- as.factor(diseniopost1$variables$Eros21)
diseniopost1$variables$Eros22 <- as.factor(diseniopost1$variables$Eros22)
diseniopost1$variables$Eros23 <- as.factor(diseniopost1$variables$Eros23)
diseniopost1$variables$Eros24 <- as.factor(diseniopost1$variables$Eros24)
diseniopost1$variables$Eros25 <- as.factor(diseniopost1$variables$Eros25)
diseniopost1$variables$Eros26 <- as.factor(diseniopost1$variables$Eros26)
diseniopost1$variables$Eros27 <- as.factor(diseniopost1$variables$Eros27)
diseniopost1$variables$Eros37 <- as.factor(diseniopost1$variables$Eros37)
diseniopost1$variables$Eros36 <- as.factor(diseniopost1$variables$Eros36)
diseniopost1$variables$Eros35 <- as.factor(diseniopost1$variables$Eros35)
diseniopost1$variables$Eros34 <- as.factor(diseniopost1$variables$Eros34)
diseniopost1$variables$Eros33 <- as.factor(diseniopost1$variables$Eros33)
diseniopost1$variables$Eros32 <- as.factor(diseniopost1$variables$Eros32)
diseniopost1$variables$Eros31 <- as.factor(diseniopost1$variables$Eros31)
diseniopost1$variables$Eros41 <- as.factor(diseniopost1$variables$Eros41)
diseniopost1$variables$Eros42 <- as.factor(diseniopost1$variables$Eros42)
diseniopost1$variables$Eros43 <- as.factor(diseniopost1$variables$Eros43)
diseniopost1$variables$Eros44 <- as.factor(diseniopost1$variables$Eros44)
diseniopost1$variables$Eros45 <- as.factor(diseniopost1$variables$Eros45)
diseniopost1$variables$Eros46 <- as.factor(diseniopost1$variables$Eros46)
diseniopost1$variables$Eros47 <- as.factor(diseniopost1$variables$Eros47)
save.image("~/Dropbox/odontologia/maestria licet/octubre 2013/datos_licet_20102013.RData")
summary(diseniopost1$variables[, 456:483])
## Eros17 Eros16 Eros15 Eros14 Eros13 Eros12
## 0 :1032 0 :841 0 :996 0 :916 0 :898 0 :607
## 1 : 3 1 :271 1 : 37 1 :112 1 : 79 1 :111
## NA's: 119 2 : 22 2 : 2 2 : 7 2 : 54 2 :212
## 3 : 2 NA's:119 NA's:119 3 : 4 3 :206
## NA's: 18 NA's:119 NA's: 18
## Eros11 Eros21 Eros22 Eros23 Eros24 Eros25
## 0 :560 0 :561 0 :601 0 :912 0 :943 0 :1007
## 1 : 64 1 : 73 1 :122 1 : 76 1 : 88 1 : 26
## 2 :235 2 :236 2 :212 2 : 38 2 : 4 2 : 2
## 3 :277 3 :266 3 :201 3 : 8 NA's:119 NA's: 119
## NA's: 18 NA's: 18 NA's: 18 NA's:120
## Eros26 Eros27 Eros37 Eros36 Eros35 Eros34
## 0 :889 0 :1034 0 :1032 0 :911 0 :1011 0 :1009
## 1 :225 1 : 1 1 : 2 1 :208 1 : 24 1 : 25
## 2 : 19 NA's: 119 2 : 1 2 : 16 NA's: 119 2 : 1
## 3 : 3 NA's: 119 3 : 1 NA's: 119
## NA's: 18 NA's: 18
## Eros33 Eros32 Eros31 Eros41 Eros42 Eros43
## 0 :943 0 :735 0 :684 0 :677 0 :734 0 :945
## 1 : 73 1 :221 1 :200 1 :194 1 :208 1 : 66
## 2 : 16 2 :133 2 :199 2 :212 2 :145 2 : 20
## 3 : 3 3 : 47 3 : 53 3 : 53 3 : 49 3 : 4
## NA's:119 NA's: 18 NA's: 18 NA's: 18 NA's: 18 NA's:119
## Eros44 Eros45 Eros46 Eros47
## 0 :1004 0 :1016 0 :884 0 :1029
## 1 : 29 1 : 18 1 :237 1 : 5
## 2 : 2 3 : 1 2 : 15 3 : 1
## NA's: 119 NA's: 119 NA's: 18 NA's: 119
##
ero17 <- svymean(~Eros17, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero17 * 100, 1)
## mean SE DEff
## Eros170 9,99e+01 6,06e-04 0,43
## Eros171 1,00e-01 6,06e-04 0,43
ero16 <- svymean(~Eros16, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero16 * 100, 1)
## mean SE DEff
## Eros160 75,50000 0,02623 4,40
## Eros161 22,00000 0,02361 3,85
## Eros162 2,50000 0,00822 3,34
## Eros163 0,10000 0,00104 1,23
ero15 <- svymean(~Eros15, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero15 * 100, 1)
## mean SE DEff
## Eros150 95,50000 0,00709 1,27
## Eros151 3,90000 0,00740 1,57
## Eros152 0,60000 0,00410 3,17
ero14 <- svymean(~Eros14, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero14 * 100, 1)
## mean SE DEff
## Eros140 88,50000 0,01471 2,30
## Eros141 10,10000 0,01130 1,52
## Eros142 1,40000 0,00871 5,91
ero13 <- svymean(~Eros13, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero13 * 100, 1)
## mean SE DEff
## Eros130 86,30000 0,02753 6,91
## Eros131 7,10000 0,01148 2,16
## Eros132 5,80000 0,01692 5,66
## Eros133 0,80000 0,00344 1,52
ero12 <- svymean(~Eros12, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero12 * 100, 1)
## mean SE DEff
## Eros120 53,6000 0,0404 7,76
## Eros121 9,3000 0,0140 2,76
## Eros122 15,8000 0,0176 2,75
## Eros123 21,2000 0,0435 13,41
ero11 <- svymean(~Eros11, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero11 * 100, 1)
## mean SE DEff
## Eros110 49,4000 0,0398 7,52
## Eros111 6,1000 0,0107 2,37
## Eros112 17,9000 0,0189 2,88
## Eros113 26,6000 0,0392 9,33
ero21 <- svymean(~Eros21, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero21 * 100, 1)
## mean SE DEff
## Eros210 49,9000 0,0353 5,89
## Eros211 6,8000 0,0123 2,82
## Eros212 18,2000 0,0227 4,11
## Eros213 25,1000 0,0386 9,36
ero22 <- svymean(~Eros22, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero22 * 100, 1)
## mean SE DEff
## Eros220 53,0000 0,0346 5,68
## Eros221 10,8000 0,0191 4,47
## Eros222 16,3000 0,0164 2,33
## Eros223 19,9000 0,0378 10,62
ero23 <- svymean(~Eros23, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero23 * 100, 1)
## mean SE DEff
## Eros230 88,60000 0,02367 6,00
## Eros231 5,80000 0,00797 1,26
## Eros232 4,30000 0,01809 8,54
## Eros233 1,30000 0,00397 1,36
ero24 <- svymean(~Eros24, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero24 * 100, 1)
## mean SE DEff
## Eros240 92,50000 0,01401 3,04
## Eros241 6,30000 0,01430 3,75
## Eros242 1,30000 0,00986 8,43
ero25 <- svymean(~Eros25, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero25 * 100, 1)
## mean SE DEff
## Eros250 97,20000 0,00936 3,42
## Eros251 2,30000 0,00587 1,67
## Eros252 0,60000 0,00410 3,17
ero26 <- svymean(~Eros26, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero26 * 100, 1)
## mean SE DEff
## Eros260 79,70000 0,02580 4,87
## Eros261 18,10000 0,02285 4,18
## Eros262 2,00000 0,00818 3,99
## Eros263 0,20000 0,00136 1,11
ero27 <- svymean(~Eros27, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero27 * 100, 1)
## mean SE DEff
## Eros270 1,00e+02 2,06e-04 0,23
## Eros271 0,00e+00 2,06e-04 0,23
ero31 <- svymean(~Eros31, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero31 * 100, 1)
## mean SE DEff
## Eros310 62,1000 0,0349 6,12
## Eros311 14,9000 0,0199 3,70
## Eros312 15,5000 0,0194 3,41
## Eros313 7,5000 0,0253 10,88
ero32 <- svymean(~Eros32, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero32 * 100, 1)
## mean SE DEff
## Eros320 65,6000 0,0336 5,93
## Eros321 17,0000 0,0182 2,77
## Eros322 10,0000 0,0122 1,97
## Eros323 7,4000 0,0283 13,81
ero33 <- svymean(~Eros33, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero33 * 100, 1)
## mean SE DEff
## Eros330 89,20000 0,02873 9,26
## Eros331 7,40000 0,01341 2,82
## Eros332 2,60000 0,01429 8,60
## Eros333 0,70000 0,00303 1,37
ero34 <- svymean(~Eros34, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero34 * 100, 1)
## mean SE DEff
## Eros340 96,40000 0,01475 6,68
## Eros341 3,30000 0,01222 5,04
## Eros342 0,30000 0,00296 2,77
ero35 <- svymean(~Eros35, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero35 * 100, 1)
## mean SE DEff
## Eros350 96,8000 0,0126 5,45
## Eros351 3,2000 0,0126 5,45
ero36 <- svymean(~Eros36, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero36 * 100, 1)
## mean SE DEff
## Eros360 8,28e+01 2,06e-02 3,53
## Eros361 1,56e+01 1,93e-02 3,34
## Eros362 1,50e+00 6,42e-03 3,26
## Eros363 1,00e-01 6,59e-04 0,78
ero37 <- svymean(~Eros37, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero37 * 100, 1)
## mean SE DEff
## Eros370 9,96e+01 2,94e-03 2,29
## Eros371 1,00e-01 4,87e-04 0,39
## Eros372 3,00e-01 2,96e-03 2,77
ero41 <- svymean(~Eros41, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero41 * 100, 1)
## mean SE DEff
## Eros410 61,4000 0,0364 6,61
## Eros411 14,9000 0,0194 3,53
## Eros412 16,0000 0,0203 3,63
## Eros413 7,6000 0,0254 10,83
ero42 <- svymean(~Eros42, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero42 * 100, 1)
## mean SE DEff
## Eros420 64,9000 0,0356 6,58
## Eros421 17,3000 0,0155 2,00
## Eros422 10,2000 0,0129 2,16
## Eros423 7,6000 0,0284 13,67
ero43 <- svymean(~Eros43, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero43 * 100, 1)
## mean SE DEff
## Eros430 88,70000 0,02905 9,10
## Eros431 7,30000 0,01360 2,96
## Eros432 3,40000 0,01888 11,56
## Eros433 0,60000 0,00339 2,23
ero44 <- svymean(~Eros44, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero44 * 100, 1)
## mean SE DEff
## Eros440 96,00000 0,01332 5,03
## Eros441 3,50000 0,01061 3,62
## Eros442 0,50000 0,00323 2,35
ero45 <- svymean(~Eros45, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero45 * 100, 1)
## mean SE DEff
## Eros450 97,80000 0,00690 2,40
## Eros451 2,00000 0,00652 2,29
## Eros453 0,10000 0,00133 1,39
ero46 <- svymean(~Eros46, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero46 * 100, 1)
## mean SE DEff
## Eros460 79,90000 0,02424 4,34
## Eros461 18,20000 0,02303 4,22
## Eros462 1,90000 0,00507 1,65
ero47 <- svymean(~Eros47, diseniopost1, na.rm = TRUE, deff = TRUE)
round(ero47 * 100, 1)
## mean SE DEff
## Eros470 99,10000 0,00623 4,78
## Eros471 0,70000 0,00609 5,41
## Eros473 0,10000 0,00133 1,39
svychisq(~Eros21 + Sexo.rec, diseniopost1, statistic = "Wald")
##
## Design-based Wald test of association
##
## data: svychisq(~Eros21 + Sexo.rec, diseniopost1, statistic = "Wald")
## F = 0,6561, ndf = 3, ddf = 39, p-value = 0,584