INITIALIZATION OF DIRECTORY AND LIBRARIES
######################################
# SETTING THE WORKING DIRECTORY
######################################
setwd("C:/Users/John/Desktop/Statistics Masters/Survey Operations/Data Analysis")
library(corrgram)
library(dplyr)
library(tidyverse)
library(caret)
library(mlbench)
library(ROCR)
library(corrplot)
library(psy)
library(Hmisc)
library(DescTools)
library(pROC)
library(car)
DATA PREPARATION AND EXPLORATION
######################################
# LOADING THE DATA
######################################
KA.df <- read.csv('OBJ2RAW_NEW.csv',
na.strings=c("NA","NaN"," ",""),
stringsAsFactors = F)
dim(KA.df)
## [1] 632 20
colnames(KA.df)
## [1] "KVAM_CATEG" "KVPD_CATEG" "KLAP_PERCT" "KVCO_CATEG" "APVS_SCORE"
## [6] "APSI_SCORE" "APVT_SCORE" "PDEX_SCORE" "RESP_SEX" "RESP_RELGN"
## [11] "RESP_RELAT" "RESP_NKIDS" "RESP_HSTAT" "RESP_AGE" "RESP_ISTAT"
## [16] "RESP_CSTAT" "RESP_ESTAT" "RESP_EDUC" "RESP_MINC" "RESP_HEXP"
summary(KA.df)
## KVAM_CATEG KVPD_CATEG KLAP_PERCT KVCO_CATEG
## Length:632 Length:632 Min. : 0.00 Length:632
## Class :character Class :character 1st Qu.: 40.00 Class :character
## Mode :character Mode :character Median : 60.00 Mode :character
## Mean : 56.71
## 3rd Qu.: 80.00
## Max. :100.00
## APVS_SCORE APSI_SCORE APVT_SCORE PDEX_SCORE
## Min. : 3.000 Min. :12.00 Min. : 4.00 Min. :0.00
## 1st Qu.: 7.000 1st Qu.:21.00 1st Qu.:10.00 1st Qu.:1.00
## Median : 8.000 Median :22.00 Median :12.00 Median :2.00
## Mean : 8.454 Mean :22.41 Mean :11.48 Mean :2.35
## 3rd Qu.:10.000 3rd Qu.:24.00 3rd Qu.:13.00 3rd Qu.:3.00
## Max. :15.000 Max. :30.00 Max. :19.00 Max. :6.00
## RESP_SEX RESP_RELGN RESP_RELAT RESP_NKIDS
## Length:632 Length:632 Length:632 Min. : 1.000
## Class :character Class :character Class :character 1st Qu.: 1.000
## Mode :character Mode :character Mode :character Median : 2.000
## Mean : 2.233
## 3rd Qu.: 3.000
## Max. :13.000
## RESP_HSTAT RESP_AGE RESP_ISTAT RESP_CSTAT
## Min. : 1.00 Min. :18.00 Length:632 Length:632
## 1st Qu.: 8.00 1st Qu.:28.75 Class :character Class :character
## Median : 9.00 Median :34.00 Mode :character Mode :character
## Mean : 8.53 Mean :36.46
## 3rd Qu.:10.00 3rd Qu.:42.00
## Max. :10.00 Max. :81.00
## RESP_ESTAT RESP_EDUC RESP_MINC
## Length:632 Length:632 Length:632
## Class :character Class :character Class :character
## Mode :character Mode :character Mode :character
##
##
##
## RESP_HEXP
## Length:632
## Class :character
## Mode :character
##
##
##
######################################
# CHECKING DATA QUALITY
######################################
(KA.df.qualitycheck <- data.frame(
Column.Index=c(1:length(names(KA.df))),
Column.Name= names(KA.df),
Column.Type=sapply(KA.df, function(x) typeof(x)),
Row.Count=sapply(KA.df, function(x) nrow(KA.df)),
NA.Count=sapply(KA.df,function(x)sum(is.na(x))),
Fill.Rate=sapply(KA.df,function(x)(sum(!is.na(x))/nrow(KA.df))),
Unique.Count=sapply(KA.df, function(x) length(unique(x))),row.names=NULL))
## Column.Index Column.Name Column.Type Row.Count NA.Count Fill.Rate
## 1 1 KVAM_CATEG character 632 0 1
## 2 2 KVPD_CATEG character 632 0 1
## 3 3 KLAP_PERCT integer 632 0 1
## 4 4 KVCO_CATEG character 632 0 1
## 5 5 APVS_SCORE integer 632 0 1
## 6 6 APSI_SCORE integer 632 0 1
## 7 7 APVT_SCORE integer 632 0 1
## 8 8 PDEX_SCORE integer 632 0 1
## 9 9 RESP_SEX character 632 0 1
## 10 10 RESP_RELGN character 632 0 1
## 11 11 RESP_RELAT character 632 0 1
## 12 12 RESP_NKIDS integer 632 0 1
## 13 13 RESP_HSTAT integer 632 0 1
## 14 14 RESP_AGE integer 632 0 1
## 15 15 RESP_ISTAT character 632 0 1
## 16 16 RESP_CSTAT character 632 0 1
## 17 17 RESP_ESTAT character 632 0 1
## 18 18 RESP_EDUC character 632 0 1
## 19 19 RESP_MINC character 632 0 1
## 20 20 RESP_HEXP character 632 0 1
## Unique.Count
## 1 2
## 2 2
## 3 6
## 4 3
## 5 13
## 6 19
## 7 16
## 8 7
## 9 2
## 10 4
## 11 3
## 12 11
## 13 8
## 14 55
## 15 4
## 16 3
## 17 2
## 18 3
## 19 4
## 20 3
######################################
# ISOLATING THE NUMERIC COLUMNS
######################################
KA.df.numeric <- KA.df[,which(sapply(KA.df, function(x) typeof(x))=="integer")]
######################################
# TESTING CORRELATION FOR THE NUMERIC COLUMNS
######################################
KA.df.numeric.corr.test <- cor.mtest(KA.df.numeric,
method = "spearman",
conf.level = .95)
corrplot(cor(KA.df.numeric,method = "spearman"),
method = "circle",
type = "upper",
order = "original",
tl.col = "black",
tl.cex = 0.75,
tl.srt = 90,
sig.level = 0.05,
p.mat = KA.df.numeric.corr.test$p,
insig = "blank")
######################################
# EVALUATING BOTH DEPENDENT VARIABLES
######################################
DV.df <- read.csv('DVBattle.csv',
na.strings=c("NA","NaN"," ",""),
stringsAsFactors = F)
dim(DV.df)
## [1] 632 4
colnames(DV.df)
## [1] "KVAM_PERCT" "KVPD_PERCT" "KVAM_CATEG" "KVPD_CATEG"
summary(DV.df)
## KVAM_PERCT KVPD_PERCT KVAM_CATEG KVPD_CATEG
## Min. :21.05 Min. :24.00 Length:632 Length:632
## 1st Qu.:57.89 1st Qu.:68.00 Class :character Class :character
## Median :68.42 Median :76.00 Mode :character Mode :character
## Mean :66.93 Mean :74.61
## 3rd Qu.:73.68 3rd Qu.:84.00
## Max. :94.74 Max. :96.00
######################################
# OBTAINING THE CORRELATION USING THE CONTINUOUS VALUES
######################################
ggplot(DV.df, aes(DV.df$KVAM_PERCT,
DV.df$KVPD_PERCT,
color = DV.df$KVAM_PERCT)) +
geom_point(shape = 16,
size = 5,
show.legend = FALSE) +
theme_minimal() +
labs(x = "KVAM") +
labs(y = "KVPD")
cor(DV.df$KVAM_PERCT,
DV.df$KVPD_PERCT,
method = c("pearson"))
## [1] 0.2053432
cor.test(DV.df$KVAM_PERCT,
DV.df$KVPD_PERCT,
method=c("pearson"))
##
## Pearson's product-moment correlation
##
## data: DV.df$KVAM_PERCT and DV.df$KVPD_PERCT
## t = 5.2663, df = 630, p-value = 1.913e-07
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1294257 0.2788674
## sample estimates:
## cor
## 0.2053432
######################################
# OBTAINING THE RELATIONSHIP USING THE DICHOTOMIZED VALUES
######################################
DV.df.relationship <- table(DV.df$KVAM_CATEG,
DV.df$KVPD_CATEG)
DV.df.relationship
##
## KNOW NOT_KNOW
## KNOW 408 58
## NOT_KNOW 121 45
prop.table(DV.df.relationship, 1)
##
## KNOW NOT_KNOW
## KNOW 0.8755365 0.1244635
## NOT_KNOW 0.7289157 0.2710843
chisq.test(DV.df.relationship)
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: DV.df.relationship
## X-squared = 18.229, df = 1, p-value = 1.959e-05
CramerV(DV.df.relationship,
conf.level=0.95)
## Cramer V lwr.ci upr.ci
## 0.17470132 0.09674427 0.25266395
######################################
# PREPARING THE DATA FOR MODELING
######################################
######################################
# RECODING THE DEPENDENT VARIABLES
######################################
KA.df$KVAM <- ifelse(KA.df$KVAM_CATEG == "KNOW",1,0)
KA.df$KVPD <- ifelse(KA.df$KVPD_CATEG == "KNOW",1,0)
######################################
# SETTING THE CATEGORICAL VARIABLE LEVELS
######################################
######################################
# TREATING CATEGORICAL VARIABLES AS NOMINAL CATEGORIES
######################################
KA.df$KVCO_CATEG <- as.factor(KA.df$KVCO_CATEG)
KA.df$KVCO_CATEG <- relevel(KA.df$KVCO_CATEG, "NOT_AWARE")
factor(KA.df$KVCO_CATEG)
## [1] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE
## [8] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE
## [15] FUL_AWARE PAR_AWARE FUL_AWARE PAR_AWARE FUL_AWARE PAR_AWARE FUL_AWARE
## [22] FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE
## [29] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [36] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [43] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE PAR_AWARE
## [50] PAR_AWARE FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE
## [57] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [64] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [71] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE
## [78] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE PAR_AWARE PAR_AWARE
## [85] PAR_AWARE PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [92] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE
## [99] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [106] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [113] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [120] FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [127] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [134] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [141] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [148] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [155] FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE
## [162] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [169] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [176] FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [183] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE
## [190] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [197] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE
## [204] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [211] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [218] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [225] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [232] PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [239] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [246] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [253] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [260] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [267] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE
## [274] FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [281] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [288] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [295] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [302] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [309] FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [316] FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [323] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [330] FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [337] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [344] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [351] PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [358] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [365] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE
## [372] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE
## [379] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [386] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [393] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [400] FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [407] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [414] PAR_AWARE PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [421] FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [428] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [435] FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE NOT_AWARE
## [442] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [449] FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [456] FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE PAR_AWARE FUL_AWARE FUL_AWARE
## [463] PAR_AWARE FUL_AWARE PAR_AWARE PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [470] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE
## [477] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [484] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [491] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [498] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [505] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE PAR_AWARE FUL_AWARE
## [512] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [519] FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [526] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [533] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [540] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [547] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [554] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [561] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [568] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [575] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [582] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [589] PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [596] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [603] FUL_AWARE PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [610] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [617] FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE
## [624] NOT_AWARE PAR_AWARE FUL_AWARE FUL_AWARE FUL_AWARE FUL_AWARE NOT_AWARE
## [631] FUL_AWARE FUL_AWARE
## Levels: NOT_AWARE FUL_AWARE PAR_AWARE
KA.df$RESP_SEX <- as.factor(KA.df$RESP_SEX)
KA.df$RESP_SEX <- relevel(KA.df$RESP_SEX, "MALE")
factor(KA.df$RESP_SEX)
## [1] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE MALE FEMALE FEMALE FEMALE
## [11] FEMALE MALE MALE FEMALE FEMALE MALE FEMALE FEMALE FEMALE FEMALE
## [21] FEMALE FEMALE FEMALE FEMALE FEMALE MALE FEMALE FEMALE FEMALE MALE
## [31] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [41] FEMALE FEMALE FEMALE MALE FEMALE FEMALE FEMALE MALE MALE FEMALE
## [51] FEMALE FEMALE FEMALE FEMALE FEMALE MALE FEMALE FEMALE FEMALE FEMALE
## [61] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [71] MALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE MALE FEMALE
## [81] FEMALE MALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [91] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [101] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [111] FEMALE FEMALE FEMALE FEMALE FEMALE MALE FEMALE MALE FEMALE FEMALE
## [121] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [131] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [141] FEMALE FEMALE FEMALE FEMALE FEMALE MALE FEMALE FEMALE FEMALE FEMALE
## [151] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [161] FEMALE FEMALE FEMALE FEMALE FEMALE MALE FEMALE FEMALE FEMALE FEMALE
## [171] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE MALE
## [181] FEMALE FEMALE MALE MALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [191] FEMALE FEMALE FEMALE FEMALE MALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [201] FEMALE FEMALE MALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE MALE
## [211] MALE MALE MALE FEMALE MALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [221] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE MALE FEMALE MALE FEMALE
## [231] FEMALE MALE FEMALE FEMALE MALE FEMALE FEMALE MALE FEMALE FEMALE
## [241] FEMALE MALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [251] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [261] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [271] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [281] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [291] FEMALE MALE MALE FEMALE FEMALE MALE FEMALE FEMALE FEMALE FEMALE
## [301] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [311] FEMALE MALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [321] FEMALE FEMALE FEMALE MALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [331] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [341] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [351] MALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [361] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [371] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE MALE FEMALE
## [381] FEMALE MALE FEMALE FEMALE FEMALE FEMALE MALE FEMALE FEMALE FEMALE
## [391] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [401] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [411] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [421] FEMALE FEMALE FEMALE FEMALE MALE FEMALE FEMALE MALE FEMALE FEMALE
## [431] FEMALE FEMALE FEMALE FEMALE FEMALE MALE FEMALE FEMALE FEMALE FEMALE
## [441] MALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [451] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE MALE FEMALE FEMALE
## [461] FEMALE MALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE MALE
## [471] MALE MALE FEMALE FEMALE MALE MALE FEMALE FEMALE MALE FEMALE
## [481] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE MALE
## [491] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE MALE FEMALE MALE MALE
## [501] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [511] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [521] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [531] FEMALE MALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [541] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [551] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE MALE FEMALE
## [561] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE MALE
## [571] FEMALE FEMALE FEMALE FEMALE MALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [581] FEMALE MALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [591] FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [601] MALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE FEMALE
## [611] FEMALE FEMALE FEMALE MALE FEMALE FEMALE MALE MALE FEMALE FEMALE
## [621] FEMALE FEMALE FEMALE FEMALE FEMALE MALE FEMALE FEMALE FEMALE FEMALE
## [631] MALE MALE
## Levels: MALE FEMALE
KA.df$RESP_RELGN <- as.factor(KA.df$RESP_RELGN)
KA.df$RESP_RELGN <- relevel(KA.df$RESP_RELGN, "OTHERS")
factor(KA.df$RESP_RELGN)
## [1] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC BORNAGAIN CATHOLIC
## [8] CATHOLIC INC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [15] INC BORNAGAIN CATHOLIC CATHOLIC BORNAGAIN CATHOLIC CATHOLIC
## [22] CATHOLIC INC INC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [29] CATHOLIC CATHOLIC CATHOLIC CATHOLIC INC CATHOLIC CATHOLIC
## [36] OTHERS CATHOLIC INC INC CATHOLIC CATHOLIC CATHOLIC
## [43] CATHOLIC BORNAGAIN CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [50] CATHOLIC INC CATHOLIC INC CATHOLIC CATHOLIC CATHOLIC
## [57] OTHERS CATHOLIC CATHOLIC CATHOLIC INC INC CATHOLIC
## [64] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [71] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [78] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC OTHERS OTHERS
## [85] CATHOLIC OTHERS CATHOLIC INC BORNAGAIN CATHOLIC CATHOLIC
## [92] CATHOLIC CATHOLIC CATHOLIC OTHERS CATHOLIC OTHERS CATHOLIC
## [99] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [106] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [113] CATHOLIC CATHOLIC INC CATHOLIC OTHERS INC INC
## [120] CATHOLIC CATHOLIC CATHOLIC INC BORNAGAIN CATHOLIC CATHOLIC
## [127] BORNAGAIN CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [134] CATHOLIC OTHERS CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [141] CATHOLIC CATHOLIC CATHOLIC CATHOLIC BORNAGAIN CATHOLIC BORNAGAIN
## [148] CATHOLIC CATHOLIC INC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [155] CATHOLIC CATHOLIC CATHOLIC CATHOLIC INC CATHOLIC CATHOLIC
## [162] INC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [169] BORNAGAIN CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [176] CATHOLIC INC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [183] BORNAGAIN BORNAGAIN CATHOLIC CATHOLIC CATHOLIC BORNAGAIN CATHOLIC
## [190] CATHOLIC CATHOLIC CATHOLIC CATHOLIC INC CATHOLIC CATHOLIC
## [197] CATHOLIC CATHOLIC CATHOLIC CATHOLIC BORNAGAIN CATHOLIC CATHOLIC
## [204] BORNAGAIN INC INC CATHOLIC CATHOLIC OTHERS CATHOLIC
## [211] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC BORNAGAIN BORNAGAIN
## [218] BORNAGAIN INC CATHOLIC BORNAGAIN CATHOLIC CATHOLIC CATHOLIC
## [225] CATHOLIC INC OTHERS CATHOLIC CATHOLIC CATHOLIC BORNAGAIN
## [232] INC CATHOLIC INC CATHOLIC CATHOLIC BORNAGAIN CATHOLIC
## [239] INC CATHOLIC OTHERS CATHOLIC CATHOLIC INC INC
## [246] OTHERS BORNAGAIN CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [253] CATHOLIC BORNAGAIN CATHOLIC CATHOLIC CATHOLIC CATHOLIC OTHERS
## [260] CATHOLIC CATHOLIC CATHOLIC BORNAGAIN CATHOLIC INC CATHOLIC
## [267] CATHOLIC CATHOLIC INC CATHOLIC CATHOLIC BORNAGAIN INC
## [274] INC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [281] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC BORNAGAIN CATHOLIC
## [288] BORNAGAIN OTHERS INC CATHOLIC CATHOLIC CATHOLIC INC
## [295] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC INC
## [302] INC INC BORNAGAIN CATHOLIC BORNAGAIN OTHERS CATHOLIC
## [309] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC OTHERS CATHOLIC
## [316] CATHOLIC CATHOLIC CATHOLIC OTHERS CATHOLIC CATHOLIC CATHOLIC
## [323] OTHERS CATHOLIC CATHOLIC CATHOLIC BORNAGAIN INC CATHOLIC
## [330] INC CATHOLIC CATHOLIC CATHOLIC INC CATHOLIC CATHOLIC
## [337] BORNAGAIN CATHOLIC CATHOLIC INC CATHOLIC INC INC
## [344] INC INC INC CATHOLIC CATHOLIC INC CATHOLIC
## [351] INC CATHOLIC CATHOLIC CATHOLIC CATHOLIC BORNAGAIN CATHOLIC
## [358] CATHOLIC CATHOLIC CATHOLIC CATHOLIC INC CATHOLIC CATHOLIC
## [365] CATHOLIC INC CATHOLIC CATHOLIC CATHOLIC INC CATHOLIC
## [372] INC CATHOLIC CATHOLIC INC CATHOLIC CATHOLIC CATHOLIC
## [379] CATHOLIC CATHOLIC OTHERS CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [386] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC OTHERS
## [393] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC INC OTHERS
## [400] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [407] CATHOLIC CATHOLIC CATHOLIC INC CATHOLIC INC CATHOLIC
## [414] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [421] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [428] CATHOLIC CATHOLIC INC CATHOLIC CATHOLIC OTHERS OTHERS
## [435] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC INC CATHOLIC
## [442] OTHERS INC CATHOLIC CATHOLIC BORNAGAIN CATHOLIC BORNAGAIN
## [449] CATHOLIC CATHOLIC INC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [456] CATHOLIC CATHOLIC CATHOLIC CATHOLIC INC CATHOLIC CATHOLIC
## [463] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC BORNAGAIN CATHOLIC
## [470] CATHOLIC CATHOLIC INC INC CATHOLIC CATHOLIC CATHOLIC
## [477] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [484] OTHERS CATHOLIC CATHOLIC CATHOLIC INC INC OTHERS
## [491] CATHOLIC CATHOLIC CATHOLIC INC INC CATHOLIC CATHOLIC
## [498] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC BORNAGAIN
## [505] CATHOLIC BORNAGAIN CATHOLIC BORNAGAIN CATHOLIC CATHOLIC BORNAGAIN
## [512] CATHOLIC CATHOLIC CATHOLIC CATHOLIC INC CATHOLIC OTHERS
## [519] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [526] OTHERS OTHERS CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [533] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [540] CATHOLIC BORNAGAIN CATHOLIC CATHOLIC CATHOLIC BORNAGAIN CATHOLIC
## [547] OTHERS CATHOLIC BORNAGAIN CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [554] OTHERS CATHOLIC OTHERS BORNAGAIN CATHOLIC CATHOLIC CATHOLIC
## [561] BORNAGAIN CATHOLIC CATHOLIC CATHOLIC CATHOLIC BORNAGAIN CATHOLIC
## [568] BORNAGAIN CATHOLIC CATHOLIC OTHERS CATHOLIC CATHOLIC CATHOLIC
## [575] CATHOLIC INC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [582] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC OTHERS CATHOLIC
## [589] CATHOLIC BORNAGAIN INC INC CATHOLIC INC CATHOLIC
## [596] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC BORNAGAIN CATHOLIC
## [603] OTHERS CATHOLIC CATHOLIC INC CATHOLIC CATHOLIC CATHOLIC
## [610] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [617] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [624] CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC CATHOLIC
## [631] CATHOLIC CATHOLIC
## Levels: OTHERS BORNAGAIN CATHOLIC INC
KA.df$RESP_RELAT <- as.factor(KA.df$RESP_RELAT)
KA.df$RESP_RELAT <- relevel(KA.df$RESP_RELAT, "GUARDIAN")
factor(KA.df$RESP_RELAT)
## [1] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER FATHER
## [8] MOTHER MOTHER MOTHER MOTHER FATHER GUARDIAN GUARDIAN
## [15] MOTHER FATHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [22] MOTHER MOTHER MOTHER MOTHER FATHER MOTHER MOTHER
## [29] MOTHER FATHER MOTHER MOTHER GUARDIAN GUARDIAN MOTHER
## [36] GUARDIAN GUARDIAN MOTHER MOTHER MOTHER MOTHER GUARDIAN
## [43] MOTHER FATHER MOTHER MOTHER GUARDIAN FATHER FATHER
## [50] MOTHER MOTHER GUARDIAN MOTHER MOTHER MOTHER FATHER
## [57] GUARDIAN GUARDIAN MOTHER MOTHER GUARDIAN GUARDIAN GUARDIAN
## [64] MOTHER MOTHER MOTHER GUARDIAN GUARDIAN MOTHER MOTHER
## [71] FATHER GUARDIAN GUARDIAN MOTHER MOTHER MOTHER GUARDIAN
## [78] MOTHER FATHER MOTHER MOTHER FATHER MOTHER GUARDIAN
## [85] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [92] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [99] GUARDIAN MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [106] MOTHER GUARDIAN MOTHER MOTHER MOTHER MOTHER MOTHER
## [113] MOTHER MOTHER MOTHER GUARDIAN MOTHER FATHER MOTHER
## [120] MOTHER MOTHER GUARDIAN MOTHER MOTHER MOTHER MOTHER
## [127] MOTHER MOTHER GUARDIAN MOTHER MOTHER GUARDIAN MOTHER
## [134] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [141] MOTHER MOTHER MOTHER MOTHER MOTHER FATHER GUARDIAN
## [148] MOTHER GUARDIAN MOTHER GUARDIAN MOTHER MOTHER MOTHER
## [155] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER GUARDIAN
## [162] MOTHER MOTHER MOTHER MOTHER FATHER MOTHER MOTHER
## [169] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [176] MOTHER MOTHER FATHER GUARDIAN FATHER MOTHER MOTHER
## [183] FATHER FATHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [190] MOTHER MOTHER MOTHER MOTHER MOTHER FATHER MOTHER
## [197] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER FATHER
## [204] GUARDIAN MOTHER MOTHER MOTHER MOTHER MOTHER FATHER
## [211] FATHER GUARDIAN FATHER MOTHER FATHER MOTHER MOTHER
## [218] MOTHER MOTHER MOTHER MOTHER GUARDIAN MOTHER MOTHER
## [225] MOTHER MOTHER GUARDIAN MOTHER FATHER MOTHER MOTHER
## [232] FATHER MOTHER MOTHER FATHER MOTHER MOTHER FATHER
## [239] MOTHER MOTHER MOTHER FATHER MOTHER MOTHER MOTHER
## [246] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [253] GUARDIAN MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [260] GUARDIAN MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [267] MOTHER GUARDIAN MOTHER MOTHER MOTHER MOTHER MOTHER
## [274] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [281] GUARDIAN MOTHER MOTHER MOTHER MOTHER GUARDIAN GUARDIAN
## [288] GUARDIAN GUARDIAN GUARDIAN MOTHER FATHER FATHER MOTHER
## [295] MOTHER GUARDIAN GUARDIAN GUARDIAN GUARDIAN GUARDIAN MOTHER
## [302] GUARDIAN MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [309] MOTHER MOTHER MOTHER FATHER MOTHER MOTHER MOTHER
## [316] GUARDIAN MOTHER MOTHER MOTHER MOTHER GUARDIAN MOTHER
## [323] MOTHER FATHER GUARDIAN MOTHER MOTHER MOTHER MOTHER
## [330] MOTHER GUARDIAN MOTHER MOTHER MOTHER GUARDIAN MOTHER
## [337] GUARDIAN MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [344] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER GUARDIAN
## [351] FATHER MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [358] MOTHER GUARDIAN MOTHER MOTHER MOTHER GUARDIAN GUARDIAN
## [365] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [372] MOTHER MOTHER MOTHER MOTHER MOTHER GUARDIAN GUARDIAN
## [379] FATHER GUARDIAN MOTHER MOTHER MOTHER MOTHER MOTHER
## [386] MOTHER GUARDIAN MOTHER MOTHER MOTHER MOTHER MOTHER
## [393] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [400] GUARDIAN MOTHER GUARDIAN GUARDIAN MOTHER MOTHER MOTHER
## [407] GUARDIAN MOTHER GUARDIAN MOTHER MOTHER MOTHER GUARDIAN
## [414] GUARDIAN MOTHER MOTHER GUARDIAN MOTHER MOTHER MOTHER
## [421] GUARDIAN GUARDIAN MOTHER MOTHER FATHER MOTHER MOTHER
## [428] FATHER MOTHER MOTHER GUARDIAN MOTHER MOTHER MOTHER
## [435] MOTHER FATHER MOTHER GUARDIAN MOTHER MOTHER FATHER
## [442] MOTHER MOTHER MOTHER GUARDIAN MOTHER MOTHER MOTHER
## [449] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [456] MOTHER MOTHER FATHER MOTHER MOTHER MOTHER FATHER
## [463] MOTHER MOTHER MOTHER MOTHER MOTHER GUARDIAN GUARDIAN
## [470] FATHER GUARDIAN GUARDIAN GUARDIAN MOTHER FATHER FATHER
## [477] MOTHER GUARDIAN FATHER MOTHER MOTHER GUARDIAN MOTHER
## [484] GUARDIAN GUARDIAN GUARDIAN MOTHER MOTHER MOTHER FATHER
## [491] MOTHER GUARDIAN MOTHER GUARDIAN MOTHER MOTHER FATHER
## [498] MOTHER GUARDIAN FATHER MOTHER MOTHER MOTHER MOTHER
## [505] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [512] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [519] MOTHER GUARDIAN MOTHER MOTHER MOTHER MOTHER MOTHER
## [526] GUARDIAN MOTHER MOTHER MOTHER MOTHER MOTHER FATHER
## [533] MOTHER MOTHER GUARDIAN MOTHER MOTHER MOTHER MOTHER
## [540] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [547] MOTHER GUARDIAN MOTHER MOTHER MOTHER MOTHER MOTHER
## [554] MOTHER MOTHER MOTHER MOTHER MOTHER FATHER MOTHER
## [561] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [568] MOTHER MOTHER FATHER MOTHER MOTHER MOTHER GUARDIAN
## [575] FATHER GUARDIAN MOTHER MOTHER MOTHER MOTHER MOTHER
## [582] FATHER MOTHER GUARDIAN MOTHER MOTHER MOTHER GUARDIAN
## [589] GUARDIAN MOTHER GUARDIAN MOTHER MOTHER MOTHER MOTHER
## [596] MOTHER MOTHER MOTHER MOTHER MOTHER FATHER MOTHER
## [603] MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [610] MOTHER MOTHER MOTHER MOTHER FATHER MOTHER MOTHER
## [617] FATHER FATHER MOTHER MOTHER MOTHER MOTHER MOTHER
## [624] MOTHER MOTHER FATHER MOTHER MOTHER MOTHER MOTHER
## [631] FATHER FATHER
## Levels: GUARDIAN FATHER MOTHER
KA.df$RESP_CSTAT <- as.factor(KA.df$RESP_CSTAT)
KA.df$RESP_CSTAT <- relevel(KA.df$RESP_CSTAT, "OTHERS")
factor(KA.df$RESP_CSTAT)
## [1] MARRIED MARRIED MARRIED OTHERS MARRIED MARRIED SINGLE SINGLE
## [9] MARRIED SINGLE SINGLE SINGLE MARRIED MARRIED MARRIED MARRIED
## [17] MARRIED SINGLE MARRIED MARRIED SINGLE MARRIED MARRIED SINGLE
## [25] SINGLE MARRIED SINGLE OTHERS SINGLE MARRIED SINGLE SINGLE
## [33] MARRIED MARRIED SINGLE OTHERS SINGLE SINGLE SINGLE MARRIED
## [41] SINGLE MARRIED SINGLE MARRIED SINGLE SINGLE MARRIED SINGLE
## [49] SINGLE SINGLE MARRIED SINGLE SINGLE MARRIED SINGLE MARRIED
## [57] MARRIED MARRIED MARRIED SINGLE MARRIED SINGLE MARRIED SINGLE
## [65] MARRIED SINGLE MARRIED MARRIED SINGLE SINGLE MARRIED MARRIED
## [73] OTHERS MARRIED MARRIED SINGLE OTHERS MARRIED SINGLE SINGLE
## [81] SINGLE SINGLE MARRIED MARRIED MARRIED MARRIED SINGLE MARRIED
## [89] SINGLE MARRIED MARRIED SINGLE MARRIED SINGLE MARRIED MARRIED
## [97] MARRIED MARRIED MARRIED SINGLE SINGLE MARRIED SINGLE SINGLE
## [105] MARRIED SINGLE MARRIED SINGLE MARRIED MARRIED SINGLE MARRIED
## [113] SINGLE SINGLE MARRIED SINGLE MARRIED MARRIED MARRIED MARRIED
## [121] MARRIED OTHERS MARRIED MARRIED MARRIED MARRIED SINGLE SINGLE
## [129] OTHERS SINGLE SINGLE MARRIED MARRIED MARRIED MARRIED SINGLE
## [137] SINGLE SINGLE MARRIED SINGLE MARRIED MARRIED SINGLE SINGLE
## [145] MARRIED MARRIED MARRIED MARRIED OTHERS MARRIED MARRIED SINGLE
## [153] MARRIED SINGLE SINGLE SINGLE SINGLE MARRIED MARRIED SINGLE
## [161] SINGLE MARRIED SINGLE MARRIED SINGLE SINGLE MARRIED MARRIED
## [169] SINGLE MARRIED MARRIED MARRIED MARRIED MARRIED MARRIED MARRIED
## [177] MARRIED SINGLE MARRIED MARRIED MARRIED SINGLE MARRIED MARRIED
## [185] MARRIED MARRIED MARRIED MARRIED SINGLE MARRIED SINGLE SINGLE
## [193] MARRIED MARRIED MARRIED MARRIED SINGLE SINGLE MARRIED MARRIED
## [201] MARRIED MARRIED MARRIED MARRIED MARRIED MARRIED SINGLE SINGLE
## [209] MARRIED MARRIED MARRIED OTHERS MARRIED MARRIED MARRIED MARRIED
## [217] MARRIED MARRIED MARRIED SINGLE SINGLE MARRIED SINGLE MARRIED
## [225] MARRIED MARRIED SINGLE MARRIED MARRIED SINGLE MARRIED MARRIED
## [233] MARRIED MARRIED SINGLE MARRIED MARRIED MARRIED MARRIED SINGLE
## [241] MARRIED MARRIED SINGLE SINGLE MARRIED MARRIED MARRIED MARRIED
## [249] MARRIED MARRIED MARRIED MARRIED MARRIED SINGLE SINGLE SINGLE
## [257] MARRIED MARRIED SINGLE SINGLE SINGLE MARRIED MARRIED MARRIED
## [265] MARRIED SINGLE SINGLE OTHERS MARRIED SINGLE MARRIED SINGLE
## [273] MARRIED MARRIED SINGLE MARRIED MARRIED SINGLE MARRIED MARRIED
## [281] MARRIED MARRIED MARRIED SINGLE MARRIED MARRIED MARRIED MARRIED
## [289] MARRIED MARRIED SINGLE MARRIED MARRIED SINGLE MARRIED SINGLE
## [297] MARRIED SINGLE SINGLE MARRIED MARRIED MARRIED MARRIED SINGLE
## [305] MARRIED MARRIED MARRIED SINGLE MARRIED MARRIED MARRIED MARRIED
## [313] SINGLE MARRIED MARRIED OTHERS SINGLE MARRIED SINGLE SINGLE
## [321] OTHERS SINGLE OTHERS SINGLE MARRIED MARRIED MARRIED OTHERS
## [329] SINGLE MARRIED SINGLE SINGLE SINGLE MARRIED MARRIED SINGLE
## [337] OTHERS MARRIED MARRIED MARRIED MARRIED MARRIED SINGLE MARRIED
## [345] MARRIED MARRIED MARRIED SINGLE MARRIED MARRIED MARRIED MARRIED
## [353] SINGLE SINGLE SINGLE SINGLE MARRIED SINGLE SINGLE SINGLE
## [361] SINGLE OTHERS MARRIED MARRIED SINGLE MARRIED MARRIED SINGLE
## [369] MARRIED MARRIED MARRIED MARRIED MARRIED MARRIED SINGLE SINGLE
## [377] OTHERS MARRIED MARRIED MARRIED MARRIED MARRIED SINGLE SINGLE
## [385] MARRIED SINGLE SINGLE MARRIED SINGLE SINGLE SINGLE SINGLE
## [393] MARRIED SINGLE SINGLE SINGLE SINGLE SINGLE MARRIED SINGLE
## [401] SINGLE SINGLE SINGLE MARRIED MARRIED MARRIED MARRIED MARRIED
## [409] OTHERS SINGLE SINGLE MARRIED OTHERS OTHERS SINGLE SINGLE
## [417] MARRIED SINGLE MARRIED SINGLE SINGLE MARRIED SINGLE SINGLE
## [425] SINGLE MARRIED SINGLE MARRIED SINGLE MARRIED MARRIED SINGLE
## [433] MARRIED MARRIED SINGLE MARRIED MARRIED OTHERS MARRIED SINGLE
## [441] MARRIED MARRIED SINGLE SINGLE MARRIED MARRIED SINGLE MARRIED
## [449] MARRIED SINGLE MARRIED MARRIED SINGLE MARRIED SINGLE MARRIED
## [457] MARRIED SINGLE MARRIED MARRIED SINGLE SINGLE MARRIED MARRIED
## [465] SINGLE SINGLE MARRIED MARRIED OTHERS MARRIED SINGLE MARRIED
## [473] MARRIED MARRIED MARRIED MARRIED SINGLE MARRIED MARRIED MARRIED
## [481] SINGLE MARRIED MARRIED MARRIED MARRIED MARRIED MARRIED MARRIED
## [489] MARRIED MARRIED SINGLE SINGLE SINGLE MARRIED MARRIED MARRIED
## [497] MARRIED MARRIED MARRIED MARRIED MARRIED MARRIED MARRIED MARRIED
## [505] MARRIED MARRIED OTHERS MARRIED OTHERS SINGLE SINGLE MARRIED
## [513] SINGLE MARRIED MARRIED MARRIED MARRIED SINGLE SINGLE MARRIED
## [521] SINGLE MARRIED SINGLE MARRIED MARRIED OTHERS MARRIED SINGLE
## [529] MARRIED MARRIED MARRIED MARRIED SINGLE MARRIED OTHERS SINGLE
## [537] MARRIED MARRIED SINGLE SINGLE SINGLE SINGLE SINGLE MARRIED
## [545] SINGLE SINGLE SINGLE MARRIED SINGLE OTHERS SINGLE MARRIED
## [553] OTHERS MARRIED MARRIED SINGLE SINGLE MARRIED MARRIED MARRIED
## [561] MARRIED MARRIED SINGLE SINGLE SINGLE MARRIED SINGLE SINGLE
## [569] SINGLE SINGLE SINGLE MARRIED SINGLE MARRIED MARRIED MARRIED
## [577] MARRIED MARRIED SINGLE SINGLE MARRIED MARRIED MARRIED MARRIED
## [585] MARRIED SINGLE MARRIED MARRIED MARRIED SINGLE OTHERS MARRIED
## [593] MARRIED MARRIED MARRIED MARRIED SINGLE MARRIED MARRIED SINGLE
## [601] MARRIED MARRIED SINGLE SINGLE MARRIED MARRIED SINGLE SINGLE
## [609] SINGLE MARRIED MARRIED MARRIED MARRIED SINGLE MARRIED SINGLE
## [617] MARRIED SINGLE OTHERS MARRIED SINGLE MARRIED SINGLE MARRIED
## [625] SINGLE MARRIED SINGLE SINGLE MARRIED MARRIED MARRIED SINGLE
## Levels: OTHERS MARRIED SINGLE
KA.df$RESP_ESTAT <- as.factor(KA.df$RESP_ESTAT)
KA.df$RESP_ESTAT <- relevel(KA.df$RESP_ESTAT, "UNEMPLOYED")
factor(KA.df$RESP_ESTAT)
## [1] UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [7] UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [13] EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED
## [19] UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [25] EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED
## [31] EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED
## [37] EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [43] EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [49] EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [55] UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED
## [61] EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED UNEMPLOYED
## [67] EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED
## [73] UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED
## [79] EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED
## [85] UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED
## [91] EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [97] EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED
## [103] UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [109] UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED
## [115] EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED
## [121] UNEMPLOYED UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED
## [127] UNEMPLOYED UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED EMPLOYED
## [133] UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED UNEMPLOYED
## [139] EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [145] UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [151] UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED
## [157] UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [163] EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [169] UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED
## [175] EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [181] UNEMPLOYED UNEMPLOYED EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [187] EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED
## [193] UNEMPLOYED EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [199] EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED
## [205] UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED EMPLOYED
## [211] EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED
## [217] UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [223] UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [229] EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [235] EMPLOYED EMPLOYED EMPLOYED EMPLOYED EMPLOYED EMPLOYED
## [241] UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED
## [247] UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [253] UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [259] UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [265] UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED
## [271] UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED
## [277] UNEMPLOYED UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED EMPLOYED
## [283] UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED
## [289] UNEMPLOYED UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED
## [295] EMPLOYED EMPLOYED EMPLOYED EMPLOYED EMPLOYED EMPLOYED
## [301] EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [307] UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [313] UNEMPLOYED EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [319] UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED
## [325] UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED EMPLOYED EMPLOYED
## [331] UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED
## [337] EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED
## [343] UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED
## [349] UNEMPLOYED UNEMPLOYED EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [355] UNEMPLOYED EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED
## [361] EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED
## [367] UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED
## [373] UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED
## [379] EMPLOYED EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED
## [385] UNEMPLOYED UNEMPLOYED EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED
## [391] EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED UNEMPLOYED
## [397] UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [403] EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [409] UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [415] UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [421] EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED EMPLOYED
## [427] UNEMPLOYED EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED
## [433] UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED
## [439] EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [445] UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [451] UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [457] UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED
## [463] UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [469] UNEMPLOYED EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [475] EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED
## [481] UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED
## [487] UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED EMPLOYED
## [493] EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED
## [499] UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [505] EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED
## [511] EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [517] UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [523] EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED
## [529] UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED
## [535] EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [541] EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [547] EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [553] EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED
## [559] EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED
## [565] UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED
## [571] UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED EMPLOYED UNEMPLOYED
## [577] EMPLOYED EMPLOYED EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [583] UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED
## [589] EMPLOYED EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED
## [595] EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED
## [601] EMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED
## [607] EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED EMPLOYED
## [613] EMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED EMPLOYED
## [619] UNEMPLOYED UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED EMPLOYED
## [625] UNEMPLOYED EMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED UNEMPLOYED
## [631] UNEMPLOYED EMPLOYED
## Levels: UNEMPLOYED EMPLOYED
KA.df$RESP_ISTAT <- as.factor(KA.df$RESP_ISTAT)
KA.df$RESP_ISTAT <- relevel(KA.df$RESP_ISTAT, "UNVACCINATED")
factor(KA.df$RESP_ISTAT)
## [1] FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [4] FULLIMMUNIZED_UNSURE PARTIMMUNIZED PARTIMMUNIZED
## [7] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [10] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [13] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## [16] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [19] FULLIMMUNIZED_SURE PARTIMMUNIZED FULLIMMUNIZED_SURE
## [22] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE PARTIMMUNIZED
## [25] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE PARTIMMUNIZED
## [28] PARTIMMUNIZED FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## [31] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [34] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [37] UNVACCINATED PARTIMMUNIZED PARTIMMUNIZED
## [40] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [43] FULLIMMUNIZED_UNSURE PARTIMMUNIZED FULLIMMUNIZED_SURE
## [46] FULLIMMUNIZED_SURE PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [49] PARTIMMUNIZED FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [52] FULLIMMUNIZED_UNSURE PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [55] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [58] FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [61] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [64] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [67] PARTIMMUNIZED FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## [70] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [73] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [76] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [79] FULLIMMUNIZED_UNSURE PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [82] PARTIMMUNIZED FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [85] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [88] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [91] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [94] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [97] FULLIMMUNIZED_SURE PARTIMMUNIZED FULLIMMUNIZED_SURE
## [100] PARTIMMUNIZED FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [103] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [106] FULLIMMUNIZED_SURE PARTIMMUNIZED PARTIMMUNIZED
## [109] PARTIMMUNIZED FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [112] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [115] FULLIMMUNIZED_SURE PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [118] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [121] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [124] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [127] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [130] FULLIMMUNIZED_SURE PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [133] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [136] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [139] FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [142] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [145] FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [148] FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [151] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [154] FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [157] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## [160] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE PARTIMMUNIZED
## [163] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [166] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## [169] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [172] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [175] FULLIMMUNIZED_UNSURE PARTIMMUNIZED PARTIMMUNIZED
## [178] UNVACCINATED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [181] FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [184] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [187] FULLIMMUNIZED_UNSURE PARTIMMUNIZED FULLIMMUNIZED_SURE
## [190] FULLIMMUNIZED_UNSURE PARTIMMUNIZED PARTIMMUNIZED
## [193] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [196] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [199] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_SURE
## [202] PARTIMMUNIZED FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [205] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## [208] PARTIMMUNIZED FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [211] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [214] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [217] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [220] FULLIMMUNIZED_UNSURE PARTIMMUNIZED PARTIMMUNIZED
## [223] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [226] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [229] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [232] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [235] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [238] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [241] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [244] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [247] FULLIMMUNIZED_SURE PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [250] FULLIMMUNIZED_UNSURE PARTIMMUNIZED PARTIMMUNIZED
## [253] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [256] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [259] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [262] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [265] FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [268] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [271] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [274] PARTIMMUNIZED FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [277] PARTIMMUNIZED FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [280] FULLIMMUNIZED_SURE PARTIMMUNIZED PARTIMMUNIZED
## [283] FULLIMMUNIZED_UNSURE PARTIMMUNIZED PARTIMMUNIZED
## [286] FULLIMMUNIZED_SURE PARTIMMUNIZED FULLIMMUNIZED_SURE
## [289] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## [292] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [295] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [298] FULLIMMUNIZED_UNSURE PARTIMMUNIZED PARTIMMUNIZED
## [301] FULLIMMUNIZED_UNSURE PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [304] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [307] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [310] PARTIMMUNIZED FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [313] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [316] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [319] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [322] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [325] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_SURE
## [328] FULLIMMUNIZED_SURE PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [331] FULLIMMUNIZED_SURE PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [334] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [337] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [340] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [343] PARTIMMUNIZED FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [346] PARTIMMUNIZED FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [349] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [352] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [355] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [358] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [361] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [364] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE PARTIMMUNIZED
## [367] FULLIMMUNIZED_UNSURE PARTIMMUNIZED FULLIMMUNIZED_SURE
## [370] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [373] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_SURE
## [376] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [379] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [382] PARTIMMUNIZED FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [385] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [388] PARTIMMUNIZED FULLIMMUNIZED_SURE PARTIMMUNIZED
## [391] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## [394] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [397] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [400] FULLIMMUNIZED_UNSURE PARTIMMUNIZED PARTIMMUNIZED
## [403] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [406] FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [409] FULLIMMUNIZED_UNSURE PARTIMMUNIZED PARTIMMUNIZED
## [412] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [415] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [418] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [421] PARTIMMUNIZED FULLIMMUNIZED_SURE PARTIMMUNIZED
## [424] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_SURE
## [427] FULLIMMUNIZED_SURE PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [430] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [433] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [436] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE PARTIMMUNIZED
## [439] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [442] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [445] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [448] FULLIMMUNIZED_SURE PARTIMMUNIZED PARTIMMUNIZED
## [451] FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [454] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## [457] PARTIMMUNIZED FULLIMMUNIZED_SURE UNVACCINATED
## [460] FULLIMMUNIZED_UNSURE PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [463] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [466] UNVACCINATED FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [469] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [472] UNVACCINATED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [475] FULLIMMUNIZED_SURE PARTIMMUNIZED PARTIMMUNIZED
## [478] PARTIMMUNIZED UNVACCINATED FULLIMMUNIZED_SURE
## [481] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## [484] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [487] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [490] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [493] FULLIMMUNIZED_UNSURE PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [496] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [499] FULLIMMUNIZED_UNSURE PARTIMMUNIZED FULLIMMUNIZED_SURE
## [502] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [505] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [508] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## [511] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## [514] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [517] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [520] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [523] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [526] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## [529] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [532] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [535] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [538] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [541] PARTIMMUNIZED FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [544] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [547] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [550] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_SURE
## [553] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [556] FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [559] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [562] FULLIMMUNIZED_SURE PARTIMMUNIZED FULLIMMUNIZED_SURE
## [565] UNVACCINATED FULLIMMUNIZED_SURE PARTIMMUNIZED
## [568] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [571] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [574] PARTIMMUNIZED PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [577] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [580] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [583] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE PARTIMMUNIZED
## [586] FULLIMMUNIZED_UNSURE PARTIMMUNIZED FULLIMMUNIZED_UNSURE
## [589] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [592] PARTIMMUNIZED FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## [595] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [598] FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE
## [601] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [604] PARTIMMUNIZED FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE
## [607] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [610] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE PARTIMMUNIZED
## [613] FULLIMMUNIZED_UNSURE PARTIMMUNIZED PARTIMMUNIZED
## [616] PARTIMMUNIZED PARTIMMUNIZED PARTIMMUNIZED
## [619] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## [622] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE PARTIMMUNIZED
## [625] FULLIMMUNIZED_SURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [628] FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE FULLIMMUNIZED_UNSURE
## [631] FULLIMMUNIZED_SURE FULLIMMUNIZED_SURE
## 4 Levels: UNVACCINATED FULLIMMUNIZED_SURE ... PARTIMMUNIZED
KA.df$RESP_EDUC <- as.factor(KA.df$RESP_EDUC)
KA.df$RESP_EDUC <- relevel(KA.df$RESP_EDUC, "EGRAD_BELOW")
factor(KA.df$RESP_EDUC)
## [1] HGRAD EGRAD_BELOW HGRAD CGRAD_ABOVE HGRAD
## [6] CGRAD_ABOVE HGRAD HGRAD HGRAD HGRAD
## [11] HGRAD HGRAD HGRAD HGRAD CGRAD_ABOVE
## [16] HGRAD CGRAD_ABOVE CGRAD_ABOVE CGRAD_ABOVE HGRAD
## [21] HGRAD EGRAD_BELOW HGRAD CGRAD_ABOVE CGRAD_ABOVE
## [26] CGRAD_ABOVE EGRAD_BELOW HGRAD HGRAD CGRAD_ABOVE
## [31] EGRAD_BELOW CGRAD_ABOVE HGRAD HGRAD EGRAD_BELOW
## [36] HGRAD CGRAD_ABOVE HGRAD HGRAD HGRAD
## [41] HGRAD CGRAD_ABOVE HGRAD HGRAD HGRAD
## [46] HGRAD CGRAD_ABOVE CGRAD_ABOVE EGRAD_BELOW HGRAD
## [51] CGRAD_ABOVE HGRAD EGRAD_BELOW EGRAD_BELOW HGRAD
## [56] CGRAD_ABOVE HGRAD HGRAD HGRAD HGRAD
## [61] CGRAD_ABOVE CGRAD_ABOVE HGRAD CGRAD_ABOVE HGRAD
## [66] HGRAD HGRAD EGRAD_BELOW CGRAD_ABOVE EGRAD_BELOW
## [71] HGRAD CGRAD_ABOVE EGRAD_BELOW CGRAD_ABOVE EGRAD_BELOW
## [76] HGRAD EGRAD_BELOW HGRAD CGRAD_ABOVE HGRAD
## [81] HGRAD EGRAD_BELOW EGRAD_BELOW HGRAD HGRAD
## [86] EGRAD_BELOW CGRAD_ABOVE HGRAD CGRAD_ABOVE HGRAD
## [91] CGRAD_ABOVE CGRAD_ABOVE HGRAD HGRAD CGRAD_ABOVE
## [96] EGRAD_BELOW CGRAD_ABOVE EGRAD_BELOW HGRAD CGRAD_ABOVE
## [101] CGRAD_ABOVE HGRAD HGRAD HGRAD HGRAD
## [106] EGRAD_BELOW CGRAD_ABOVE HGRAD HGRAD HGRAD
## [111] HGRAD CGRAD_ABOVE HGRAD HGRAD CGRAD_ABOVE
## [116] HGRAD CGRAD_ABOVE HGRAD HGRAD HGRAD
## [121] EGRAD_BELOW HGRAD CGRAD_ABOVE CGRAD_ABOVE HGRAD
## [126] HGRAD HGRAD HGRAD CGRAD_ABOVE HGRAD
## [131] EGRAD_BELOW HGRAD HGRAD HGRAD EGRAD_BELOW
## [136] HGRAD HGRAD CGRAD_ABOVE HGRAD HGRAD
## [141] CGRAD_ABOVE CGRAD_ABOVE HGRAD CGRAD_ABOVE CGRAD_ABOVE
## [146] CGRAD_ABOVE CGRAD_ABOVE HGRAD EGRAD_BELOW CGRAD_ABOVE
## [151] CGRAD_ABOVE HGRAD CGRAD_ABOVE HGRAD HGRAD
## [156] CGRAD_ABOVE HGRAD CGRAD_ABOVE HGRAD HGRAD
## [161] HGRAD HGRAD CGRAD_ABOVE HGRAD CGRAD_ABOVE
## [166] HGRAD HGRAD HGRAD HGRAD HGRAD
## [171] HGRAD CGRAD_ABOVE HGRAD HGRAD CGRAD_ABOVE
## [176] HGRAD CGRAD_ABOVE HGRAD HGRAD HGRAD
## [181] HGRAD HGRAD HGRAD CGRAD_ABOVE HGRAD
## [186] CGRAD_ABOVE HGRAD HGRAD EGRAD_BELOW EGRAD_BELOW
## [191] HGRAD HGRAD CGRAD_ABOVE HGRAD HGRAD
## [196] HGRAD HGRAD HGRAD HGRAD CGRAD_ABOVE
## [201] CGRAD_ABOVE CGRAD_ABOVE HGRAD EGRAD_BELOW CGRAD_ABOVE
## [206] HGRAD HGRAD CGRAD_ABOVE HGRAD CGRAD_ABOVE
## [211] CGRAD_ABOVE HGRAD HGRAD CGRAD_ABOVE CGRAD_ABOVE
## [216] HGRAD CGRAD_ABOVE CGRAD_ABOVE EGRAD_BELOW HGRAD
## [221] CGRAD_ABOVE HGRAD HGRAD HGRAD CGRAD_ABOVE
## [226] CGRAD_ABOVE HGRAD HGRAD CGRAD_ABOVE CGRAD_ABOVE
## [231] CGRAD_ABOVE HGRAD CGRAD_ABOVE CGRAD_ABOVE HGRAD
## [236] CGRAD_ABOVE CGRAD_ABOVE CGRAD_ABOVE CGRAD_ABOVE EGRAD_BELOW
## [241] EGRAD_BELOW CGRAD_ABOVE HGRAD HGRAD HGRAD
## [246] CGRAD_ABOVE HGRAD EGRAD_BELOW EGRAD_BELOW CGRAD_ABOVE
## [251] HGRAD HGRAD HGRAD HGRAD HGRAD
## [256] HGRAD HGRAD CGRAD_ABOVE HGRAD CGRAD_ABOVE
## [261] HGRAD HGRAD HGRAD CGRAD_ABOVE HGRAD
## [266] HGRAD HGRAD CGRAD_ABOVE HGRAD HGRAD
## [271] HGRAD HGRAD HGRAD CGRAD_ABOVE EGRAD_BELOW
## [276] HGRAD CGRAD_ABOVE HGRAD CGRAD_ABOVE HGRAD
## [281] HGRAD CGRAD_ABOVE HGRAD HGRAD HGRAD
## [286] CGRAD_ABOVE HGRAD EGRAD_BELOW EGRAD_BELOW HGRAD
## [291] HGRAD HGRAD HGRAD EGRAD_BELOW CGRAD_ABOVE
## [296] HGRAD HGRAD HGRAD EGRAD_BELOW EGRAD_BELOW
## [301] CGRAD_ABOVE HGRAD CGRAD_ABOVE HGRAD HGRAD
## [306] HGRAD CGRAD_ABOVE HGRAD HGRAD CGRAD_ABOVE
## [311] HGRAD CGRAD_ABOVE EGRAD_BELOW HGRAD CGRAD_ABOVE
## [316] HGRAD HGRAD HGRAD HGRAD CGRAD_ABOVE
## [321] HGRAD CGRAD_ABOVE HGRAD HGRAD HGRAD
## [326] EGRAD_BELOW HGRAD HGRAD HGRAD HGRAD
## [331] EGRAD_BELOW HGRAD EGRAD_BELOW CGRAD_ABOVE EGRAD_BELOW
## [336] CGRAD_ABOVE HGRAD HGRAD HGRAD EGRAD_BELOW
## [341] CGRAD_ABOVE HGRAD CGRAD_ABOVE CGRAD_ABOVE HGRAD
## [346] HGRAD CGRAD_ABOVE HGRAD HGRAD EGRAD_BELOW
## [351] HGRAD CGRAD_ABOVE HGRAD CGRAD_ABOVE HGRAD
## [356] CGRAD_ABOVE CGRAD_ABOVE EGRAD_BELOW CGRAD_ABOVE HGRAD
## [361] CGRAD_ABOVE CGRAD_ABOVE HGRAD HGRAD CGRAD_ABOVE
## [366] HGRAD HGRAD HGRAD HGRAD CGRAD_ABOVE
## [371] HGRAD CGRAD_ABOVE HGRAD EGRAD_BELOW HGRAD
## [376] HGRAD CGRAD_ABOVE CGRAD_ABOVE HGRAD HGRAD
## [381] CGRAD_ABOVE HGRAD HGRAD CGRAD_ABOVE CGRAD_ABOVE
## [386] HGRAD CGRAD_ABOVE CGRAD_ABOVE EGRAD_BELOW HGRAD
## [391] EGRAD_BELOW HGRAD HGRAD HGRAD HGRAD
## [396] HGRAD HGRAD HGRAD HGRAD EGRAD_BELOW
## [401] HGRAD CGRAD_ABOVE CGRAD_ABOVE HGRAD HGRAD
## [406] HGRAD HGRAD CGRAD_ABOVE EGRAD_BELOW HGRAD
## [411] HGRAD CGRAD_ABOVE HGRAD HGRAD HGRAD
## [416] EGRAD_BELOW HGRAD HGRAD HGRAD HGRAD
## [421] HGRAD CGRAD_ABOVE CGRAD_ABOVE HGRAD HGRAD
## [426] CGRAD_ABOVE HGRAD CGRAD_ABOVE CGRAD_ABOVE HGRAD
## [431] CGRAD_ABOVE CGRAD_ABOVE HGRAD HGRAD HGRAD
## [436] CGRAD_ABOVE CGRAD_ABOVE HGRAD CGRAD_ABOVE HGRAD
## [441] CGRAD_ABOVE HGRAD HGRAD HGRAD HGRAD
## [446] CGRAD_ABOVE CGRAD_ABOVE CGRAD_ABOVE HGRAD HGRAD
## [451] HGRAD HGRAD CGRAD_ABOVE HGRAD EGRAD_BELOW
## [456] CGRAD_ABOVE CGRAD_ABOVE HGRAD EGRAD_BELOW HGRAD
## [461] HGRAD HGRAD HGRAD HGRAD HGRAD
## [466] EGRAD_BELOW CGRAD_ABOVE CGRAD_ABOVE CGRAD_ABOVE CGRAD_ABOVE
## [471] HGRAD HGRAD HGRAD HGRAD CGRAD_ABOVE
## [476] CGRAD_ABOVE HGRAD HGRAD CGRAD_ABOVE CGRAD_ABOVE
## [481] HGRAD HGRAD HGRAD CGRAD_ABOVE EGRAD_BELOW
## [486] HGRAD HGRAD HGRAD CGRAD_ABOVE CGRAD_ABOVE
## [491] HGRAD CGRAD_ABOVE CGRAD_ABOVE HGRAD HGRAD
## [496] HGRAD CGRAD_ABOVE CGRAD_ABOVE HGRAD HGRAD
## [501] CGRAD_ABOVE HGRAD HGRAD HGRAD CGRAD_ABOVE
## [506] HGRAD HGRAD HGRAD CGRAD_ABOVE EGRAD_BELOW
## [511] CGRAD_ABOVE HGRAD CGRAD_ABOVE HGRAD HGRAD
## [516] HGRAD CGRAD_ABOVE HGRAD HGRAD EGRAD_BELOW
## [521] CGRAD_ABOVE HGRAD HGRAD HGRAD HGRAD
## [526] HGRAD HGRAD HGRAD HGRAD HGRAD
## [531] HGRAD HGRAD EGRAD_BELOW EGRAD_BELOW EGRAD_BELOW
## [536] HGRAD HGRAD HGRAD HGRAD HGRAD
## [541] CGRAD_ABOVE HGRAD CGRAD_ABOVE EGRAD_BELOW EGRAD_BELOW
## [546] HGRAD HGRAD EGRAD_BELOW HGRAD CGRAD_ABOVE
## [551] HGRAD EGRAD_BELOW EGRAD_BELOW HGRAD HGRAD
## [556] HGRAD CGRAD_ABOVE HGRAD CGRAD_ABOVE HGRAD
## [561] HGRAD HGRAD HGRAD HGRAD CGRAD_ABOVE
## [566] EGRAD_BELOW EGRAD_BELOW CGRAD_ABOVE HGRAD HGRAD
## [571] HGRAD EGRAD_BELOW HGRAD CGRAD_ABOVE CGRAD_ABOVE
## [576] HGRAD CGRAD_ABOVE CGRAD_ABOVE HGRAD HGRAD
## [581] HGRAD HGRAD HGRAD EGRAD_BELOW HGRAD
## [586] CGRAD_ABOVE HGRAD EGRAD_BELOW EGRAD_BELOW CGRAD_ABOVE
## [591] CGRAD_ABOVE HGRAD HGRAD HGRAD CGRAD_ABOVE
## [596] HGRAD HGRAD HGRAD HGRAD HGRAD
## [601] CGRAD_ABOVE HGRAD HGRAD EGRAD_BELOW HGRAD
## [606] CGRAD_ABOVE EGRAD_BELOW HGRAD HGRAD CGRAD_ABOVE
## [611] HGRAD CGRAD_ABOVE CGRAD_ABOVE HGRAD HGRAD
## [616] EGRAD_BELOW HGRAD HGRAD HGRAD CGRAD_ABOVE
## [621] CGRAD_ABOVE HGRAD CGRAD_ABOVE EGRAD_BELOW HGRAD
## [626] CGRAD_ABOVE HGRAD HGRAD EGRAD_BELOW EGRAD_BELOW
## [631] HGRAD HGRAD
## Levels: EGRAD_BELOW CGRAD_ABOVE HGRAD
KA.df$RESP_MINC <- as.factor(KA.df$RESP_MINC)
KA.df$RESP_MINC <- relevel(KA.df$RESP_MINC, "10K_BELOW")
factor(KA.df$RESP_MINC)
## [1] 10K_BELOW 10KTO19K 10K_BELOW 20KTO49K 10KTO19K 10K_BELOW 10K_BELOW
## [8] 10K_BELOW 10K_BELOW 10KTO19K 10KTO19K 50K_ABOVE 10KTO19K 20KTO49K
## [15] 10KTO19K 50K_ABOVE 50K_ABOVE 50K_ABOVE 50K_ABOVE 50K_ABOVE 10K_BELOW
## [22] 10KTO19K 20KTO49K 20KTO49K 10KTO19K 50K_ABOVE 10KTO19K 10K_BELOW
## [29] 10K_BELOW 10KTO19K 10K_BELOW 50K_ABOVE 10K_BELOW 10KTO19K 10K_BELOW
## [36] 10K_BELOW 20KTO49K 10KTO19K 10K_BELOW 10K_BELOW 20KTO49K 50K_ABOVE
## [43] 10KTO19K 20KTO49K 20KTO49K 20KTO49K 10K_BELOW 10K_BELOW 10KTO19K
## [50] 10KTO19K 10KTO19K 20KTO49K 10K_BELOW 10K_BELOW 10K_BELOW 20KTO49K
## [57] 10KTO19K 50K_ABOVE 10KTO19K 10K_BELOW 10KTO19K 20KTO49K 10KTO19K
## [64] 50K_ABOVE 10K_BELOW 20KTO49K 10KTO19K 10K_BELOW 10K_BELOW 10K_BELOW
## [71] 10K_BELOW 10K_BELOW 10K_BELOW 20KTO49K 20KTO49K 10K_BELOW 10K_BELOW
## [78] 10KTO19K 10KTO19K 10KTO19K 50K_ABOVE 10K_BELOW 10K_BELOW 10K_BELOW
## [85] 20KTO49K 10K_BELOW 50K_ABOVE 10K_BELOW 10KTO19K 10KTO19K 20KTO49K
## [92] 50K_ABOVE 50K_ABOVE 10K_BELOW 10KTO19K 10KTO19K 20KTO49K 10KTO19K
## [99] 10KTO19K 20KTO49K 20KTO49K 10KTO19K 10KTO19K 10K_BELOW 10KTO19K
## [106] 10K_BELOW 10K_BELOW 10K_BELOW 10KTO19K 10K_BELOW 10K_BELOW 10KTO19K
## [113] 10KTO19K 10KTO19K 50K_ABOVE 50K_ABOVE 50K_ABOVE 50K_ABOVE 10KTO19K
## [120] 20KTO49K 10KTO19K 50K_ABOVE 50K_ABOVE 20KTO49K 20KTO49K 10K_BELOW
## [127] 10K_BELOW 10KTO19K 10K_BELOW 10K_BELOW 10K_BELOW 10KTO19K 10KTO19K
## [134] 20KTO49K 10K_BELOW 10K_BELOW 10KTO19K 10K_BELOW 10KTO19K 10K_BELOW
## [141] 10K_BELOW 50K_ABOVE 10KTO19K 20KTO49K 10KTO19K 10KTO19K 20KTO49K
## [148] 10K_BELOW 10KTO19K 20KTO49K 10KTO19K 10KTO19K 10KTO19K 20KTO49K
## [155] 20KTO49K 50K_ABOVE 10KTO19K 20KTO49K 20KTO49K 10K_BELOW 50K_ABOVE
## [162] 10K_BELOW 20KTO49K 20KTO49K 20KTO49K 10KTO19K 10K_BELOW 10KTO19K
## [169] 10K_BELOW 10K_BELOW 10KTO19K 20KTO49K 10KTO19K 20KTO49K 50K_ABOVE
## [176] 10KTO19K 10K_BELOW 50K_ABOVE 10K_BELOW 10KTO19K 10KTO19K 10KTO19K
## [183] 10K_BELOW 10K_BELOW 10K_BELOW 10KTO19K 20KTO49K 10KTO19K 10KTO19K
## [190] 10KTO19K 10KTO19K 10KTO19K 20KTO49K 20KTO49K 10KTO19K 10K_BELOW
## [197] 10KTO19K 10K_BELOW 10K_BELOW 10KTO19K 20KTO49K 20KTO49K 20KTO49K
## [204] 10KTO19K 10KTO19K 10KTO19K 20KTO49K 10KTO19K 50K_ABOVE 10KTO19K
## [211] 50K_ABOVE 50K_ABOVE 10KTO19K 10KTO19K 50K_ABOVE 10K_BELOW 10K_BELOW
## [218] 10KTO19K 10KTO19K 10K_BELOW 20KTO49K 20KTO49K 10K_BELOW 10KTO19K
## [225] 50K_ABOVE 20KTO49K 20KTO49K 20KTO49K 10KTO19K 20KTO49K 10KTO19K
## [232] 20KTO49K 50K_ABOVE 20KTO49K 10KTO19K 20KTO49K 10K_BELOW 20KTO49K
## [239] 10KTO19K 20KTO49K 10KTO19K 10KTO19K 10K_BELOW 20KTO49K 20KTO49K
## [246] 50K_ABOVE 10KTO19K 10KTO19K 20KTO49K 50K_ABOVE 20KTO49K 20KTO49K
## [253] 20KTO49K 10K_BELOW 10KTO19K 10K_BELOW 10KTO19K 10KTO19K 10KTO19K
## [260] 50K_ABOVE 20KTO49K 10KTO19K 50K_ABOVE 10K_BELOW 10KTO19K 10KTO19K
## [267] 10KTO19K 10KTO19K 50K_ABOVE 50K_ABOVE 10K_BELOW 10KTO19K 10KTO19K
## [274] 10KTO19K 10K_BELOW 10KTO19K 10K_BELOW 10KTO19K 20KTO49K 10KTO19K
## [281] 10KTO19K 20KTO49K 10KTO19K 10KTO19K 10KTO19K 50K_ABOVE 10K_BELOW
## [288] 50K_ABOVE 50K_ABOVE 10KTO19K 10K_BELOW 10KTO19K 10K_BELOW 10K_BELOW
## [295] 50K_ABOVE 10K_BELOW 10KTO19K 10K_BELOW 10KTO19K 10K_BELOW 50K_ABOVE
## [302] 20KTO49K 20KTO49K 10K_BELOW 10KTO19K 10KTO19K 10K_BELOW 10KTO19K
## [309] 50K_ABOVE 20KTO49K 20KTO49K 50K_ABOVE 20KTO49K 20KTO49K 20KTO49K
## [316] 10K_BELOW 10K_BELOW 10K_BELOW 10KTO19K 10KTO19K 20KTO49K 20KTO49K
## [323] 20KTO49K 10K_BELOW 20KTO49K 10K_BELOW 10K_BELOW 10KTO19K 50K_ABOVE
## [330] 20KTO49K 10K_BELOW 10KTO19K 10K_BELOW 10KTO19K 10KTO19K 10KTO19K
## [337] 50K_ABOVE 10KTO19K 10K_BELOW 10KTO19K 20KTO49K 10K_BELOW 20KTO49K
## [344] 50K_ABOVE 10K_BELOW 20KTO49K 10K_BELOW 10K_BELOW 10K_BELOW 50K_ABOVE
## [351] 10KTO19K 20KTO49K 10KTO19K 20KTO49K 10KTO19K 20KTO49K 20KTO49K
## [358] 10K_BELOW 10KTO19K 10KTO19K 20KTO49K 20KTO49K 10KTO19K 10KTO19K
## [365] 20KTO49K 10KTO19K 10K_BELOW 10K_BELOW 10KTO19K 10K_BELOW 20KTO49K
## [372] 20KTO49K 10K_BELOW 10K_BELOW 20KTO49K 20KTO49K 20KTO49K 10K_BELOW
## [379] 10KTO19K 10KTO19K 20KTO49K 10KTO19K 10KTO19K 10KTO19K 10KTO19K
## [386] 10K_BELOW 20KTO49K 10KTO19K 10K_BELOW 10KTO19K 10K_BELOW 10K_BELOW
## [393] 10KTO19K 10KTO19K 10K_BELOW 10K_BELOW 10K_BELOW 20KTO49K 10K_BELOW
## [400] 10K_BELOW 10K_BELOW 10KTO19K 10KTO19K 10KTO19K 10K_BELOW 10KTO19K
## [407] 10K_BELOW 10K_BELOW 50K_ABOVE 10KTO19K 20KTO49K 20KTO49K 50K_ABOVE
## [414] 10KTO19K 10K_BELOW 10KTO19K 10KTO19K 10KTO19K 10KTO19K 10K_BELOW
## [421] 10K_BELOW 50K_ABOVE 20KTO49K 10K_BELOW 10K_BELOW 50K_ABOVE 10K_BELOW
## [428] 20KTO49K 50K_ABOVE 10KTO19K 50K_ABOVE 10K_BELOW 10KTO19K 20KTO49K
## [435] 10KTO19K 50K_ABOVE 50K_ABOVE 10KTO19K 10KTO19K 10K_BELOW 20KTO49K
## [442] 10K_BELOW 10K_BELOW 20KTO49K 10KTO19K 10KTO19K 20KTO49K 10KTO19K
## [449] 10K_BELOW 10KTO19K 20KTO49K 10KTO19K 10KTO19K 10K_BELOW 10KTO19K
## [456] 20KTO49K 20KTO49K 10K_BELOW 10K_BELOW 10KTO19K 10KTO19K 10K_BELOW
## [463] 10K_BELOW 10K_BELOW 10K_BELOW 10K_BELOW 20KTO49K 10KTO19K 20KTO49K
## [470] 20KTO49K 20KTO49K 10K_BELOW 10KTO19K 20KTO49K 50K_ABOVE 20KTO49K
## [477] 10KTO19K 20KTO49K 50K_ABOVE 50K_ABOVE 10K_BELOW 10KTO19K 10K_BELOW
## [484] 20KTO49K 20KTO49K 50K_ABOVE 10KTO19K 10KTO19K 10KTO19K 20KTO49K
## [491] 20KTO49K 50K_ABOVE 10K_BELOW 10K_BELOW 20KTO49K 10KTO19K 20KTO49K
## [498] 10KTO19K 10KTO19K 10KTO19K 20KTO49K 50K_ABOVE 10KTO19K 20KTO49K
## [505] 20KTO49K 10KTO19K 10KTO19K 20KTO49K 10K_BELOW 10K_BELOW 10KTO19K
## [512] 20KTO49K 20KTO49K 10K_BELOW 10KTO19K 20KTO49K 10KTO19K 10K_BELOW
## [519] 10K_BELOW 20KTO49K 10KTO19K 20KTO49K 20KTO49K 10K_BELOW 10KTO19K
## [526] 10K_BELOW 20KTO49K 10KTO19K 10K_BELOW 20KTO49K 20KTO49K 10KTO19K
## [533] 10K_BELOW 10K_BELOW 10KTO19K 10KTO19K 10K_BELOW 10K_BELOW 10K_BELOW
## [540] 10K_BELOW 50K_ABOVE 10KTO19K 20KTO49K 10KTO19K 10K_BELOW 10K_BELOW
## [547] 10KTO19K 10K_BELOW 10K_BELOW 10KTO19K 10K_BELOW 10K_BELOW 10KTO19K
## [554] 10K_BELOW 10K_BELOW 10KTO19K 10KTO19K 10KTO19K 20KTO49K 10KTO19K
## [561] 10KTO19K 10KTO19K 20KTO49K 10KTO19K 10K_BELOW 10KTO19K 10K_BELOW
## [568] 10KTO19K 10K_BELOW 10KTO19K 10K_BELOW 10K_BELOW 10K_BELOW 20KTO49K
## [575] 50K_ABOVE 10K_BELOW 50K_ABOVE 20KTO49K 10K_BELOW 10K_BELOW 20KTO49K
## [582] 10K_BELOW 10K_BELOW 10KTO19K 10K_BELOW 10KTO19K 20KTO49K 10KTO19K
## [589] 10K_BELOW 10KTO19K 50K_ABOVE 10K_BELOW 10K_BELOW 10KTO19K 20KTO49K
## [596] 10KTO19K 10K_BELOW 10K_BELOW 10KTO19K 50K_ABOVE 10KTO19K 10K_BELOW
## [603] 10KTO19K 50K_ABOVE 20KTO49K 10KTO19K 10KTO19K 10K_BELOW 10KTO19K
## [610] 20KTO49K 20KTO49K 20KTO49K 50K_ABOVE 10K_BELOW 10K_BELOW 10KTO19K
## [617] 10K_BELOW 10K_BELOW 50K_ABOVE 10KTO19K 20KTO49K 10KTO19K 10K_BELOW
## [624] 10K_BELOW 10KTO19K 50K_ABOVE 10K_BELOW 10KTO19K 10KTO19K 10K_BELOW
## [631] 50K_ABOVE 20KTO49K
## Levels: 10K_BELOW 10KTO19K 20KTO49K 50K_ABOVE
KA.df$RESP_HEXP <- as.factor(KA.df$RESP_HEXP)
KA.df$RESP_HEXP <- relevel(KA.df$RESP_HEXP, "5K_BELOW")
factor(KA.df$RESP_HEXP)
## [1] 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5KTO19K 5KTO19K
## [8] 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5KTO19K 5KTO19K
## [15] 5K_BELOW 5KTO19K 20K_ABOVE 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [22] 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW
## [29] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [36] 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K
## [43] 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5KTO19K 5K_BELOW 5K_BELOW
## [50] 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW
## [57] 5K_BELOW 5KTO19K 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW
## [64] 20K_ABOVE 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5KTO19K
## [71] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [78] 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW
## [85] 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW
## [92] 5K_BELOW 5KTO19K 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [99] 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW
## [106] 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW
## [113] 5K_BELOW 5K_BELOW 5KTO19K 5KTO19K 5KTO19K 5KTO19K 5KTO19K
## [120] 5K_BELOW 5K_BELOW 5KTO19K 5KTO19K 5K_BELOW 5KTO19K 5K_BELOW
## [127] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [134] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [141] 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [148] 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW
## [155] 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW
## [162] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [169] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K
## [176] 5KTO19K 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K
## [183] 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW
## [190] 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [197] 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [204] 5K_BELOW 20K_ABOVE 5K_BELOW 20K_ABOVE 5K_BELOW 5K_BELOW 5K_BELOW
## [211] 5KTO19K 5K_BELOW 5K_BELOW 5KTO19K 5KTO19K 5K_BELOW 5K_BELOW
## [218] 5K_BELOW 5KTO19K 5KTO19K 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW
## [225] 5K_BELOW 20K_ABOVE 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [232] 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW
## [239] 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K
## [246] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K
## [253] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [260] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW
## [267] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [274] 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5KTO19K 5KTO19K
## [281] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5KTO19K
## [288] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [295] 5KTO19K 5KTO19K 5KTO19K 5K_BELOW 5KTO19K 5K_BELOW 5KTO19K
## [302] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [309] 5KTO19K 5KTO19K 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 20K_ABOVE
## [316] 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K
## [323] 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K
## [330] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K
## [337] 5K_BELOW 5K_BELOW 5K_BELOW 20K_ABOVE 5KTO19K 20K_ABOVE 5K_BELOW
## [344] 5KTO19K 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW
## [351] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5KTO19K
## [358] 5K_BELOW 20K_ABOVE 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 20K_ABOVE
## [365] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K
## [372] 5KTO19K 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 20K_ABOVE 5K_BELOW
## [379] 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5KTO19K
## [386] 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5KTO19K 5KTO19K 5KTO19K
## [393] 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [400] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [407] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5KTO19K
## [414] 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW
## [421] 5KTO19K 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 20K_ABOVE 5K_BELOW
## [428] 5K_BELOW 20K_ABOVE 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [435] 5K_BELOW 5KTO19K 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [442] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [449] 5K_BELOW 5K_BELOW 5KTO19K 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW
## [456] 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [463] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5KTO19K 5KTO19K
## [470] 5KTO19K 5KTO19K 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW
## [477] 5K_BELOW 20K_ABOVE 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [484] 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5KTO19K 5KTO19K
## [491] 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K
## [498] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [505] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [512] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW
## [519] 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [526] 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [533] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [540] 5K_BELOW 5K_BELOW 5KTO19K 20K_ABOVE 5KTO19K 5K_BELOW 5K_BELOW
## [547] 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW
## [554] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [561] 5K_BELOW 5K_BELOW 5KTO19K 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW
## [568] 5K_BELOW 5KTO19K 5KTO19K 20K_ABOVE 5K_BELOW 5KTO19K 5KTO19K
## [575] 5KTO19K 5K_BELOW 5KTO19K 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW
## [582] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [589] 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [596] 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW 5KTO19K 5KTO19K
## [603] 20K_ABOVE 5KTO19K 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [610] 5K_BELOW 5KTO19K 5K_BELOW 20K_ABOVE 5K_BELOW 5K_BELOW 5K_BELOW
## [617] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5KTO19K 5K_BELOW
## [624] 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW 5K_BELOW
## [631] 5K_BELOW 5K_BELOW
## Levels: 5K_BELOW 20K_ABOVE 5KTO19K
######################################
# TREATING CATEGORICAL VARIABLES AS ORDINAL CATEGORIES
######################################
#KA.df$KVCO_CATEG <- as.factor(KA.df$KVCO_CATEG)
#KA.df$KVCO_CATEG <- factor(KA.df$KVCO_CATEG, order=TRUE,
# levels = c("NOT_AWARE", "PAR_AWARE", "FUL_AWARE"))
#factor(KA.df$KVCO_CATEG)
#KA.df$RESP_ISTAT <- as.factor(KA.df$RESP_ISTAT)
#KA.df$RESP_ISTAT <- factor(KA.df$RESP_ISTAT, order=TRUE,
# levels = c("UNVACCINATED", "PARTIMMUNIZED", "FULLIMMUNIZED_UNSURE", "FULLIMMUNIZED_SURE"))
#factor(KA.df$RESP_ISTAT)
#KA.df$RESP_EDUC <- as.factor(KA.df$RESP_EDUC)
#KA.df$RESP_EDUC <- factor(KA.df$RESP_EDUC, order=TRUE,
# levels = c("EGRAD_BELOW", "HGRAD", "CGRAD_ABOVE"))
#factor(KA.df$RESP_EDUC)
#KA.df$RESP_MINC <- as.factor(KA.df$RESP_MINC)
#KA.df$RESP_MINC <- factor(KA.df$RESP_MINC, order=TRUE,
# levels = c("10K_BELOW", "10KTO19K", "20KTO49K", "50K_ABOVE"))
#factor(KA.df$RESP_MINC)
#KA.df$RESP_HEXP <- as.factor(KA.df$RESP_HEXP)
#KA.df$RESP_HEXP <- factor(KA.df$RESP_HEXP, order=TRUE,
# levels = c("5K_BELOW", "5KTO19K", "20K_ABOVE"))
#factor(KA.df$RESP_HEXP)
LOGIT MODELING FOR KVAM
######################################
# CREATING THE LOGIT MODEL FOR KVAM
######################################
######################################
# FULL MODEL
######################################
KA.df.KVAM.logitfullmodel <- glm(KVAM ~ KLAP_PERCT +
KVCO_CATEG +
APVS_SCORE +
APSI_SCORE +
APVT_SCORE +
PDEX_SCORE +
RESP_SEX +
RESP_RELGN +
RESP_RELAT +
RESP_NKIDS +
RESP_HSTAT +
RESP_AGE +
RESP_ISTAT +
RESP_CSTAT +
RESP_ESTAT +
RESP_EDUC +
RESP_MINC +
RESP_HEXP,
family = binomial(link = 'logit'),
data=KA.df)
summary(KA.df.KVAM.logitfullmodel)
##
## Call:
## glm(formula = KVAM ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE +
## APVT_SCORE + PDEX_SCORE + RESP_SEX + RESP_RELGN + RESP_RELAT +
## RESP_NKIDS + RESP_HSTAT + RESP_AGE + RESP_ISTAT + RESP_CSTAT +
## RESP_ESTAT + RESP_EDUC + RESP_MINC + RESP_HEXP, family = binomial(link = "logit"),
## data = KA.df)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.4534 -0.9913 0.6070 0.7816 1.7763
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.364182 2.256141 -0.605 0.545410
## KLAP_PERCT 0.003380 0.004910 0.688 0.491245
## KVCO_CATEGFUL_AWARE 0.170874 1.285799 0.133 0.894278
## KVCO_CATEGPAR_AWARE -0.651525 1.313092 -0.496 0.619770
## APVS_SCORE 0.008669 0.049522 0.175 0.861038
## APSI_SCORE 0.082832 0.034767 2.382 0.017196 *
## APVT_SCORE 0.031440 0.039126 0.804 0.421652
## PDEX_SCORE 0.036103 0.076074 0.475 0.635086
## RESP_SEXFEMALE 0.774174 0.786207 0.985 0.324774
## RESP_RELGNBORNAGAIN -0.603200 0.533030 -1.132 0.257784
## RESP_RELGNCATHOLIC -0.030724 0.430542 -0.071 0.943110
## RESP_RELGNINC -0.278928 0.497597 -0.561 0.575105
## RESP_RELATFATHER -0.032647 0.816953 -0.040 0.968124
## RESP_RELATMOTHER -0.472008 0.359709 -1.312 0.189455
## RESP_NKIDS -0.022555 0.065445 -0.345 0.730362
## RESP_HSTAT 0.035555 0.063724 0.558 0.576875
## RESP_AGE -0.045189 0.013232 -3.415 0.000638 ***
## RESP_ISTATFULLIMMUNIZED_SURE 0.375328 0.938043 0.400 0.689070
## RESP_ISTATFULLIMMUNIZED_UNSURE 0.053480 0.924522 0.058 0.953871
## RESP_ISTATPARTIMMUNIZED -0.005901 0.924928 -0.006 0.994910
## RESP_CSTATMARRIED 0.124750 0.457175 0.273 0.784953
## RESP_CSTATSINGLE -0.286459 0.504332 -0.568 0.570037
## RESP_ESTATEMPLOYED -0.031669 0.217526 -0.146 0.884249
## RESP_EDUCCGRAD_ABOVE 0.900821 0.340096 2.649 0.008080 **
## RESP_EDUCHGRAD 0.716043 0.282843 2.532 0.011355 *
## RESP_MINC10KTO19K 0.196828 0.235032 0.837 0.402339
## RESP_MINC20KTO49K 0.342881 0.290248 1.181 0.237468
## RESP_MINC50K_ABOVE 0.378919 0.368790 1.027 0.304201
## RESP_HEXP20K_ABOVE 0.181182 0.621832 0.291 0.770770
## RESP_HEXP5KTO19K 0.300060 0.259556 1.156 0.247661
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 727.84 on 631 degrees of freedom
## Residual deviance: 669.57 on 602 degrees of freedom
## AIC: 729.57
##
## Number of Fisher Scoring iterations: 4
exp(coef(KA.df.KVAM.logitfullmodel))
## (Intercept) KLAP_PERCT
## 0.2555896 1.0033856
## KVCO_CATEGFUL_AWARE KVCO_CATEGPAR_AWARE
## 1.1863418 0.5212500
## APVS_SCORE APSI_SCORE
## 1.0087066 1.0863591
## APVT_SCORE PDEX_SCORE
## 1.0319396 1.0367629
## RESP_SEXFEMALE RESP_RELGNBORNAGAIN
## 2.1687993 0.5470582
## RESP_RELGNCATHOLIC RESP_RELGNINC
## 0.9697428 0.7565945
## RESP_RELATFATHER RESP_RELATMOTHER
## 0.9678804 0.6237488
## RESP_NKIDS RESP_HSTAT
## 0.9776974 1.0361950
## RESP_AGE RESP_ISTATFULLIMMUNIZED_SURE
## 0.9558165 1.4554684
## RESP_ISTATFULLIMMUNIZED_UNSURE RESP_ISTATPARTIMMUNIZED
## 1.0549360 0.9941165
## RESP_CSTATMARRIED RESP_CSTATSINGLE
## 1.1328647 0.7509180
## RESP_ESTATEMPLOYED RESP_EDUCCGRAD_ABOVE
## 0.9688276 2.4616237
## RESP_EDUCHGRAD RESP_MINC10KTO19K
## 2.0463207 1.2175350
## RESP_MINC20KTO49K RESP_MINC50K_ABOVE
## 1.4090016 1.4607051
## RESP_HEXP20K_ABOVE RESP_HEXP5KTO19K
## 1.1986332 1.3499392
vif(KA.df.KVAM.logitfullmodel)
## GVIF Df GVIF^(1/(2*Df))
## KLAP_PERCT 1.180868 1 1.086678
## KVCO_CATEG 1.238189 2 1.054865
## APVS_SCORE 1.107837 1 1.052538
## APSI_SCORE 1.105480 1 1.051418
## APVT_SCORE 1.089764 1 1.043918
## PDEX_SCORE 1.068853 1 1.033853
## RESP_SEX 7.311470 1 2.703973
## RESP_RELGN 1.213375 3 1.032759
## RESP_RELAT 13.927102 2 1.931813
## RESP_NKIDS 1.101980 1 1.049752
## RESP_HSTAT 1.079103 1 1.038799
## RESP_AGE 2.482409 1 1.575566
## RESP_ISTAT 1.115521 3 1.018387
## RESP_CSTAT 1.749167 2 1.150026
## RESP_ESTAT 1.287273 1 1.134580
## RESP_EDUC 1.439660 2 1.095380
## RESP_MINC 1.439404 3 1.062585
## RESP_HEXP 1.174621 2 1.041057
######################################
# ZERO MODEL
######################################
KA.df.KVAM.logitzeromodel <- glm(KVAM ~ 1,
family = binomial(link = 'logit'),
data=KA.df)
summary(KA.df.KVAM.logitzeromodel)
##
## Call:
## glm(formula = KVAM ~ 1, family = binomial(link = "logit"), data = KA.df)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.6352 -1.6352 0.7806 0.7806 0.7806
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.03220 0.09039 11.42 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 727.84 on 631 degrees of freedom
## Residual deviance: 727.84 on 631 degrees of freedom
## AIC: 729.84
##
## Number of Fisher Scoring iterations: 4
exp(coef(KA.df.KVAM.logitzeromodel))
## (Intercept)
## 2.807229
######################################
# APPLYING BACKWARD ELIMINATION PROCEDURE
######################################
KA.df.KVAM.backwardelimination = step(KA.df.KVAM.logitfullmodel)
## Start: AIC=729.57
## KVAM ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_RELGN + RESP_RELAT + RESP_NKIDS +
## RESP_HSTAT + RESP_AGE + RESP_ISTAT + RESP_CSTAT + RESP_ESTAT +
## RESP_EDUC + RESP_MINC + RESP_HEXP
##
## Df Deviance AIC
## - RESP_MINC 3 671.42 725.42
## - RESP_ISTAT 3 671.74 725.74
## - RESP_RELGN 3 672.58 726.58
## - RESP_HEXP 2 670.97 726.97
## - RESP_RELAT 2 671.35 727.35
## - RESP_ESTAT 1 669.59 727.59
## - APVS_SCORE 1 669.60 727.60
## - RESP_NKIDS 1 669.68 727.68
## - PDEX_SCORE 1 669.79 727.79
## - RESP_HSTAT 1 669.87 727.87
## - KLAP_PERCT 1 670.04 728.04
## - APVT_SCORE 1 670.21 728.21
## - RESP_SEX 1 670.49 728.49
## - RESP_CSTAT 2 672.70 728.70
## <none> 669.57 729.57
## - KVCO_CATEG 2 675.55 731.55
## - APSI_SCORE 1 675.26 733.26
## - RESP_EDUC 2 677.37 733.37
## - RESP_AGE 1 681.59 739.59
##
## Step: AIC=725.42
## KVAM ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_RELGN + RESP_RELAT + RESP_NKIDS +
## RESP_HSTAT + RESP_AGE + RESP_ISTAT + RESP_CSTAT + RESP_ESTAT +
## RESP_EDUC + RESP_HEXP
##
## Df Deviance AIC
## - RESP_ISTAT 3 673.97 721.97
## - RESP_RELGN 3 674.34 722.34
## - RESP_RELAT 2 673.23 723.23
## - RESP_HEXP 2 673.26 723.26
## - RESP_ESTAT 1 671.42 723.42
## - APVS_SCORE 1 671.47 723.47
## - RESP_NKIDS 1 671.64 723.64
## - PDEX_SCORE 1 671.76 723.76
## - RESP_HSTAT 1 671.91 723.91
## - KLAP_PERCT 1 671.97 723.97
## - APVT_SCORE 1 672.00 724.00
## - RESP_SEX 1 672.32 724.32
## - RESP_CSTAT 2 675.00 725.00
## <none> 671.42 725.42
## - KVCO_CATEG 2 677.23 727.23
## - APSI_SCORE 1 676.82 728.82
## - RESP_EDUC 2 681.13 731.13
## - RESP_AGE 1 683.03 735.03
##
## Step: AIC=721.97
## KVAM ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_RELGN + RESP_RELAT + RESP_NKIDS +
## RESP_HSTAT + RESP_AGE + RESP_CSTAT + RESP_ESTAT + RESP_EDUC +
## RESP_HEXP
##
## Df Deviance AIC
## - RESP_RELGN 3 676.92 718.92
## - RESP_RELAT 2 675.74 719.74
## - RESP_HEXP 2 675.82 719.82
## - RESP_ESTAT 1 673.98 719.98
## - APVS_SCORE 1 674.00 720.00
## - RESP_NKIDS 1 674.22 720.22
## - PDEX_SCORE 1 674.27 720.27
## - RESP_HSTAT 1 674.45 720.45
## - KLAP_PERCT 1 674.60 720.60
## - APVT_SCORE 1 674.72 720.72
## - RESP_SEX 1 674.84 720.84
## - RESP_CSTAT 2 677.79 721.79
## <none> 673.97 721.97
## - KVCO_CATEG 2 680.23 724.23
## - APSI_SCORE 1 679.21 725.21
## - RESP_EDUC 2 683.64 727.64
## - RESP_AGE 1 685.99 731.99
##
## Step: AIC=718.92
## KVAM ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_RELAT + RESP_NKIDS + RESP_HSTAT +
## RESP_AGE + RESP_CSTAT + RESP_ESTAT + RESP_EDUC + RESP_HEXP
##
## Df Deviance AIC
## - RESP_RELAT 2 678.87 716.87
## - RESP_ESTAT 1 676.93 716.93
## - APVS_SCORE 1 676.97 716.97
## - RESP_HEXP 2 679.01 717.01
## - RESP_NKIDS 1 677.24 717.24
## - PDEX_SCORE 1 677.29 717.29
## - RESP_HSTAT 1 677.59 717.59
## - KLAP_PERCT 1 677.63 717.63
## - RESP_SEX 1 677.74 717.74
## - APVT_SCORE 1 677.79 717.79
## - RESP_CSTAT 2 680.26 718.26
## <none> 676.92 718.92
## - KVCO_CATEG 2 682.93 720.93
## - APSI_SCORE 1 681.58 721.58
## - RESP_EDUC 2 685.63 723.63
## - RESP_AGE 1 689.28 729.28
##
## Step: AIC=716.87
## KVAM ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_NKIDS + RESP_HSTAT + RESP_AGE +
## RESP_CSTAT + RESP_ESTAT + RESP_EDUC + RESP_HEXP
##
## Df Deviance AIC
## - RESP_ESTAT 1 678.87 714.87
## - APVS_SCORE 1 678.94 714.94
## - RESP_NKIDS 1 679.07 715.07
## - PDEX_SCORE 1 679.13 715.13
## - RESP_HEXP 2 681.23 715.23
## - KLAP_PERCT 1 679.48 715.48
## - RESP_HSTAT 1 679.51 715.51
## - RESP_CSTAT 2 681.64 715.64
## - APVT_SCORE 1 680.03 716.03
## - RESP_SEX 1 680.23 716.23
## <none> 678.87 716.87
## - KVCO_CATEG 2 684.51 718.51
## - APSI_SCORE 1 683.35 719.35
## - RESP_EDUC 2 687.06 721.06
## - RESP_AGE 1 690.14 726.14
##
## Step: AIC=714.87
## KVAM ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_NKIDS + RESP_HSTAT + RESP_AGE +
## RESP_CSTAT + RESP_EDUC + RESP_HEXP
##
## Df Deviance AIC
## - APVS_SCORE 1 678.94 712.94
## - RESP_NKIDS 1 679.07 713.07
## - PDEX_SCORE 1 679.13 713.13
## - RESP_HEXP 2 681.24 713.24
## - KLAP_PERCT 1 679.48 713.48
## - RESP_HSTAT 1 679.51 713.51
## - RESP_CSTAT 2 681.65 713.65
## - APVT_SCORE 1 680.03 714.03
## - RESP_SEX 1 680.40 714.40
## <none> 678.87 714.87
## - KVCO_CATEG 2 684.57 716.57
## - APSI_SCORE 1 683.36 717.36
## - RESP_EDUC 2 687.11 719.11
## - RESP_AGE 1 690.14 724.14
##
## Step: AIC=712.94
## KVAM ~ KLAP_PERCT + KVCO_CATEG + APSI_SCORE + APVT_SCORE + PDEX_SCORE +
## RESP_SEX + RESP_NKIDS + RESP_HSTAT + RESP_AGE + RESP_CSTAT +
## RESP_EDUC + RESP_HEXP
##
## Df Deviance AIC
## - RESP_NKIDS 1 679.13 711.13
## - PDEX_SCORE 1 679.19 711.19
## - RESP_HEXP 2 681.30 711.30
## - KLAP_PERCT 1 679.55 711.55
## - RESP_HSTAT 1 679.56 711.56
## - RESP_CSTAT 2 681.69 711.69
## - APVT_SCORE 1 680.12 712.12
## - RESP_SEX 1 680.50 712.50
## <none> 678.94 712.94
## - KVCO_CATEG 2 684.57 714.57
## - APSI_SCORE 1 683.67 715.67
## - RESP_EDUC 2 687.11 717.11
## - RESP_AGE 1 690.28 722.28
##
## Step: AIC=711.13
## KVAM ~ KLAP_PERCT + KVCO_CATEG + APSI_SCORE + APVT_SCORE + PDEX_SCORE +
## RESP_SEX + RESP_HSTAT + RESP_AGE + RESP_CSTAT + RESP_EDUC +
## RESP_HEXP
##
## Df Deviance AIC
## - PDEX_SCORE 1 679.35 709.35
## - RESP_HEXP 2 681.42 709.42
## - KLAP_PERCT 1 679.69 709.69
## - RESP_HSTAT 1 679.72 709.72
## - RESP_CSTAT 2 681.89 709.89
## - APVT_SCORE 1 680.32 710.32
## - RESP_SEX 1 680.67 710.67
## <none> 679.13 711.13
## - KVCO_CATEG 2 684.70 712.70
## - APSI_SCORE 1 684.07 714.07
## - RESP_EDUC 2 687.89 715.89
## - RESP_AGE 1 690.36 720.36
##
## Step: AIC=709.35
## KVAM ~ KLAP_PERCT + KVCO_CATEG + APSI_SCORE + APVT_SCORE + RESP_SEX +
## RESP_HSTAT + RESP_AGE + RESP_CSTAT + RESP_EDUC + RESP_HEXP
##
## Df Deviance AIC
## - RESP_HEXP 2 681.67 707.67
## - RESP_HSTAT 1 679.91 707.91
## - KLAP_PERCT 1 679.96 707.96
## - RESP_CSTAT 2 682.18 708.18
## - APVT_SCORE 1 680.51 708.51
## - RESP_SEX 1 680.91 708.91
## <none> 679.35 709.35
## - KVCO_CATEG 2 684.87 710.87
## - APSI_SCORE 1 684.24 712.24
## - RESP_EDUC 2 688.07 714.07
## - RESP_AGE 1 690.39 718.39
##
## Step: AIC=707.67
## KVAM ~ KLAP_PERCT + KVCO_CATEG + APSI_SCORE + APVT_SCORE + RESP_SEX +
## RESP_HSTAT + RESP_AGE + RESP_CSTAT + RESP_EDUC
##
## Df Deviance AIC
## - RESP_HSTAT 1 682.36 706.36
## - KLAP_PERCT 1 682.40 706.40
## - RESP_CSTAT 2 684.78 706.78
## - RESP_SEX 1 682.97 706.97
## - APVT_SCORE 1 683.07 707.07
## <none> 681.67 707.67
## - KVCO_CATEG 2 686.94 708.94
## - APSI_SCORE 1 686.73 710.73
## - RESP_EDUC 2 691.54 713.54
## - RESP_AGE 1 692.69 716.69
##
## Step: AIC=706.36
## KVAM ~ KLAP_PERCT + KVCO_CATEG + APSI_SCORE + APVT_SCORE + RESP_SEX +
## RESP_AGE + RESP_CSTAT + RESP_EDUC
##
## Df Deviance AIC
## - KLAP_PERCT 1 683.15 705.15
## - RESP_CSTAT 2 685.54 705.54
## - APVT_SCORE 1 683.74 705.74
## - RESP_SEX 1 683.74 705.74
## <none> 682.36 706.36
## - KVCO_CATEG 2 687.71 707.71
## - APSI_SCORE 1 687.27 709.27
## - RESP_EDUC 2 692.38 712.38
## - RESP_AGE 1 693.54 715.54
##
## Step: AIC=705.15
## KVAM ~ KVCO_CATEG + APSI_SCORE + APVT_SCORE + RESP_SEX + RESP_AGE +
## RESP_CSTAT + RESP_EDUC
##
## Df Deviance AIC
## - RESP_CSTAT 2 686.26 704.26
## - APVT_SCORE 1 684.82 704.82
## - RESP_SEX 1 685.05 705.05
## <none> 683.15 705.15
## - KVCO_CATEG 2 689.57 707.57
## - APSI_SCORE 1 688.32 708.32
## - RESP_EDUC 2 693.94 711.94
## - RESP_AGE 1 694.09 714.09
##
## Step: AIC=704.26
## KVAM ~ KVCO_CATEG + APSI_SCORE + APVT_SCORE + RESP_SEX + RESP_AGE +
## RESP_EDUC
##
## Df Deviance AIC
## - RESP_SEX 1 687.89 703.89
## - APVT_SCORE 1 687.94 703.94
## <none> 686.26 704.26
## - KVCO_CATEG 2 693.16 707.16
## - APSI_SCORE 1 691.49 707.49
## - RESP_AGE 1 695.55 711.55
## - RESP_EDUC 2 697.97 711.97
##
## Step: AIC=703.89
## KVAM ~ KVCO_CATEG + APSI_SCORE + APVT_SCORE + RESP_AGE + RESP_EDUC
##
## Df Deviance AIC
## - APVT_SCORE 1 689.53 703.53
## <none> 687.89 703.89
## - KVCO_CATEG 2 695.41 707.41
## - APSI_SCORE 1 693.41 707.41
## - RESP_EDUC 2 698.61 710.61
## - RESP_AGE 1 697.15 711.15
##
## Step: AIC=703.53
## KVAM ~ KVCO_CATEG + APSI_SCORE + RESP_AGE + RESP_EDUC
##
## Df Deviance AIC
## <none> 689.53 703.53
## - KVCO_CATEG 2 697.56 707.56
## - APSI_SCORE 1 696.32 708.32
## - RESP_EDUC 2 699.83 709.83
## - RESP_AGE 1 698.87 710.87
summary(KA.df.KVAM.backwardelimination)
##
## Call:
## glm(formula = KVAM ~ KVCO_CATEG + APSI_SCORE + RESP_AGE + RESP_EDUC,
## family = binomial(link = "logit"), data = KA.df)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.0664 -1.0276 0.6501 0.7803 1.6157
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.872855 1.524555 -0.573 0.56696
## KVCO_CATEGFUL_AWARE 0.359423 1.250258 0.287 0.77375
## KVCO_CATEGPAR_AWARE -0.529161 1.275755 -0.415 0.67830
## APSI_SCORE 0.085460 0.032839 2.602 0.00926 **
## RESP_AGE -0.025296 0.008244 -3.068 0.00215 **
## RESP_EDUCCGRAD_ABOVE 0.972855 0.303032 3.210 0.00133 **
## RESP_EDUCHGRAD 0.686233 0.268828 2.553 0.01069 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 727.84 on 631 degrees of freedom
## Residual deviance: 689.53 on 625 degrees of freedom
## AIC: 703.53
##
## Number of Fisher Scoring iterations: 4
######################################
# APPLYING FORWARD SELECTION PROCEDURE
######################################
KA.df.KVAM.forwardselection = step(KA.df.KVAM.logitzeromodel,
scope=list(lower=formula(KA.df.KVAM.logitzeromodel),
upper=formula(KA.df.KVAM.logitfullmodel)),
direction="forward")
## Start: AIC=729.84
## KVAM ~ 1
##
## Df Deviance AIC
## + RESP_EDUC 2 712.48 718.48
## + RESP_AGE 1 718.47 722.47
## + KVCO_CATEG 2 716.60 722.60
## + APSI_SCORE 1 721.71 725.71
## + KLAP_PERCT 1 722.53 726.53
## + APVT_SCORE 1 724.62 728.62
## + RESP_HEXP 2 723.66 729.66
## <none> 727.84 729.84
## + RESP_MINC 3 722.05 730.05
## + RESP_RELAT 2 724.64 730.64
## + RESP_HSTAT 1 726.65 730.65
## + RESP_SEX 1 726.79 730.79
## + RESP_ISTAT 3 723.25 731.25
## + RESP_ESTAT 1 727.48 731.48
## + RESP_NKIDS 1 727.50 731.50
## + RESP_CSTAT 2 725.54 731.54
## + PDEX_SCORE 1 727.81 731.81
## + APVS_SCORE 1 727.82 731.82
## + RESP_RELGN 3 726.51 734.51
##
## Step: AIC=718.48
## KVAM ~ RESP_EDUC
##
## Df Deviance AIC
## + RESP_AGE 1 704.25 712.25
## + APSI_SCORE 1 706.01 714.01
## + KVCO_CATEG 2 705.40 715.40
## + APVT_SCORE 1 708.72 716.72
## + KLAP_PERCT 1 709.21 717.21
## + RESP_SEX 1 710.19 718.19
## <none> 712.48 718.48
## + RESP_RELAT 2 709.21 719.21
## + RESP_HSTAT 1 711.57 719.57
## + RESP_HEXP 2 709.76 719.76
## + APVS_SCORE 1 712.10 720.10
## + RESP_ISTAT 3 708.31 720.31
## + PDEX_SCORE 1 712.44 720.44
## + RESP_NKIDS 1 712.48 720.48
## + RESP_ESTAT 1 712.48 720.48
## + RESP_CSTAT 2 710.95 720.95
## + RESP_RELGN 3 709.99 721.99
## + RESP_MINC 3 710.41 722.41
##
## Step: AIC=712.25
## KVAM ~ RESP_EDUC + RESP_AGE
##
## Df Deviance AIC
## + APSI_SCORE 1 697.56 707.56
## + KVCO_CATEG 2 696.32 708.32
## + KLAP_PERCT 1 700.45 710.45
## + APVT_SCORE 1 700.62 710.62
## + RESP_SEX 1 701.85 711.85
## <none> 704.25 712.25
## + RESP_CSTAT 2 700.82 712.82
## + RESP_RELAT 2 701.17 713.17
## + RESP_HEXP 2 701.23 713.23
## + RESP_HSTAT 1 703.26 713.26
## + PDEX_SCORE 1 704.03 714.03
## + APVS_SCORE 1 704.06 714.06
## + RESP_NKIDS 1 704.18 714.18
## + RESP_ESTAT 1 704.25 714.25
## + RESP_ISTAT 3 700.31 714.31
## + RESP_MINC 3 701.09 715.09
## + RESP_RELGN 3 701.89 715.89
##
## Step: AIC=707.56
## KVAM ~ RESP_EDUC + RESP_AGE + APSI_SCORE
##
## Df Deviance AIC
## + KVCO_CATEG 2 689.53 703.53
## + KLAP_PERCT 1 694.39 706.39
## + RESP_SEX 1 695.40 707.40
## + APVT_SCORE 1 695.41 707.41
## <none> 697.56 707.56
## + RESP_CSTAT 2 694.29 708.29
## + RESP_HSTAT 1 696.39 708.39
## + RESP_RELAT 2 694.80 708.80
## + RESP_HEXP 2 694.87 708.87
## + PDEX_SCORE 1 697.25 709.25
## + APVS_SCORE 1 697.56 709.56
## + RESP_ESTAT 1 697.56 709.56
## + RESP_NKIDS 1 697.56 709.56
## + RESP_ISTAT 3 693.61 709.61
## + RESP_MINC 3 694.06 710.06
## + RESP_RELGN 3 694.56 710.56
##
## Step: AIC=703.53
## KVAM ~ RESP_EDUC + RESP_AGE + APSI_SCORE + KVCO_CATEG
##
## Df Deviance AIC
## <none> 689.53 703.53
## + APVT_SCORE 1 687.89 703.89
## + RESP_SEX 1 687.94 703.94
## + KLAP_PERCT 1 688.02 704.02
## + RESP_HSTAT 1 688.56 704.56
## + RESP_HEXP 2 686.61 704.61
## + RESP_CSTAT 2 686.65 704.65
## + RESP_RELAT 2 687.07 705.07
## + PDEX_SCORE 1 689.21 705.21
## + RESP_ESTAT 1 689.45 705.45
## + APVS_SCORE 1 689.46 705.46
## + RESP_NKIDS 1 689.50 705.50
## + RESP_MINC 3 686.01 706.01
## + RESP_RELGN 3 686.12 706.12
## + RESP_ISTAT 3 686.42 706.42
summary(KA.df.KVAM.forwardselection)
##
## Call:
## glm(formula = KVAM ~ RESP_EDUC + RESP_AGE + APSI_SCORE + KVCO_CATEG,
## family = binomial(link = "logit"), data = KA.df)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.0664 -1.0276 0.6501 0.7803 1.6157
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.872855 1.524555 -0.573 0.56696
## RESP_EDUCCGRAD_ABOVE 0.972855 0.303032 3.210 0.00133 **
## RESP_EDUCHGRAD 0.686233 0.268828 2.553 0.01069 *
## RESP_AGE -0.025296 0.008244 -3.068 0.00215 **
## APSI_SCORE 0.085460 0.032839 2.602 0.00926 **
## KVCO_CATEGFUL_AWARE 0.359423 1.250258 0.287 0.77375
## KVCO_CATEGPAR_AWARE -0.529161 1.275755 -0.415 0.67830
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 727.84 on 631 degrees of freedom
## Residual deviance: 689.53 on 625 degrees of freedom
## AIC: 703.53
##
## Number of Fisher Scoring iterations: 4
######################################
# APPLYING STEPWISE REGRESSION PROCEDURE
######################################
KA.df.KVAM.stepwiseregression = step(KA.df.KVAM.logitzeromodel,
scope=list(lower=formula(KA.df.KVAM.logitzeromodel),
upper=formula(KA.df.KVAM.logitfullmodel)),
direction="both")
## Start: AIC=729.84
## KVAM ~ 1
##
## Df Deviance AIC
## + RESP_EDUC 2 712.48 718.48
## + RESP_AGE 1 718.47 722.47
## + KVCO_CATEG 2 716.60 722.60
## + APSI_SCORE 1 721.71 725.71
## + KLAP_PERCT 1 722.53 726.53
## + APVT_SCORE 1 724.62 728.62
## + RESP_HEXP 2 723.66 729.66
## <none> 727.84 729.84
## + RESP_MINC 3 722.05 730.05
## + RESP_RELAT 2 724.64 730.64
## + RESP_HSTAT 1 726.65 730.65
## + RESP_SEX 1 726.79 730.79
## + RESP_ISTAT 3 723.25 731.25
## + RESP_ESTAT 1 727.48 731.48
## + RESP_NKIDS 1 727.50 731.50
## + RESP_CSTAT 2 725.54 731.54
## + PDEX_SCORE 1 727.81 731.81
## + APVS_SCORE 1 727.82 731.82
## + RESP_RELGN 3 726.51 734.51
##
## Step: AIC=718.48
## KVAM ~ RESP_EDUC
##
## Df Deviance AIC
## + RESP_AGE 1 704.25 712.25
## + APSI_SCORE 1 706.01 714.01
## + KVCO_CATEG 2 705.40 715.40
## + APVT_SCORE 1 708.72 716.72
## + KLAP_PERCT 1 709.21 717.21
## + RESP_SEX 1 710.19 718.19
## <none> 712.48 718.48
## + RESP_RELAT 2 709.21 719.21
## + RESP_HSTAT 1 711.57 719.57
## + RESP_HEXP 2 709.76 719.76
## + APVS_SCORE 1 712.10 720.10
## + RESP_ISTAT 3 708.31 720.31
## + PDEX_SCORE 1 712.44 720.44
## + RESP_NKIDS 1 712.48 720.48
## + RESP_ESTAT 1 712.48 720.48
## + RESP_CSTAT 2 710.95 720.95
## + RESP_RELGN 3 709.99 721.99
## + RESP_MINC 3 710.41 722.41
## - RESP_EDUC 2 727.84 729.84
##
## Step: AIC=712.25
## KVAM ~ RESP_EDUC + RESP_AGE
##
## Df Deviance AIC
## + APSI_SCORE 1 697.56 707.56
## + KVCO_CATEG 2 696.32 708.32
## + KLAP_PERCT 1 700.45 710.45
## + APVT_SCORE 1 700.62 710.62
## + RESP_SEX 1 701.85 711.85
## <none> 704.25 712.25
## + RESP_CSTAT 2 700.82 712.82
## + RESP_RELAT 2 701.17 713.17
## + RESP_HEXP 2 701.23 713.23
## + RESP_HSTAT 1 703.26 713.26
## + PDEX_SCORE 1 704.03 714.03
## + APVS_SCORE 1 704.06 714.06
## + RESP_NKIDS 1 704.18 714.18
## + RESP_ESTAT 1 704.25 714.25
## + RESP_ISTAT 3 700.31 714.31
## + RESP_MINC 3 701.09 715.09
## + RESP_RELGN 3 701.89 715.89
## - RESP_AGE 1 712.48 718.48
## - RESP_EDUC 2 718.47 722.47
##
## Step: AIC=707.56
## KVAM ~ RESP_EDUC + RESP_AGE + APSI_SCORE
##
## Df Deviance AIC
## + KVCO_CATEG 2 689.53 703.53
## + KLAP_PERCT 1 694.39 706.39
## + RESP_SEX 1 695.40 707.40
## + APVT_SCORE 1 695.41 707.41
## <none> 697.56 707.56
## + RESP_CSTAT 2 694.29 708.29
## + RESP_HSTAT 1 696.39 708.39
## + RESP_RELAT 2 694.80 708.80
## + RESP_HEXP 2 694.87 708.87
## + PDEX_SCORE 1 697.25 709.25
## + APVS_SCORE 1 697.56 709.56
## + RESP_ESTAT 1 697.56 709.56
## + RESP_NKIDS 1 697.56 709.56
## + RESP_ISTAT 3 693.61 709.61
## + RESP_MINC 3 694.06 710.06
## + RESP_RELGN 3 694.56 710.56
## - APSI_SCORE 1 704.25 712.25
## - RESP_AGE 1 706.01 714.01
## - RESP_EDUC 2 712.11 718.11
##
## Step: AIC=703.53
## KVAM ~ RESP_EDUC + RESP_AGE + APSI_SCORE + KVCO_CATEG
##
## Df Deviance AIC
## <none> 689.53 703.53
## + APVT_SCORE 1 687.89 703.89
## + RESP_SEX 1 687.94 703.94
## + KLAP_PERCT 1 688.02 704.02
## + RESP_HSTAT 1 688.56 704.56
## + RESP_HEXP 2 686.61 704.61
## + RESP_CSTAT 2 686.65 704.65
## + RESP_RELAT 2 687.07 705.07
## + PDEX_SCORE 1 689.21 705.21
## + RESP_ESTAT 1 689.45 705.45
## + APVS_SCORE 1 689.46 705.46
## + RESP_NKIDS 1 689.50 705.50
## + RESP_MINC 3 686.01 706.01
## + RESP_RELGN 3 686.12 706.12
## + RESP_ISTAT 3 686.42 706.42
## - KVCO_CATEG 2 697.56 707.56
## - APSI_SCORE 1 696.32 708.32
## - RESP_EDUC 2 699.83 709.83
## - RESP_AGE 1 698.87 710.87
summary(KA.df.KVAM.stepwiseregression )
##
## Call:
## glm(formula = KVAM ~ RESP_EDUC + RESP_AGE + APSI_SCORE + KVCO_CATEG,
## family = binomial(link = "logit"), data = KA.df)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.0664 -1.0276 0.6501 0.7803 1.6157
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.872855 1.524555 -0.573 0.56696
## RESP_EDUCCGRAD_ABOVE 0.972855 0.303032 3.210 0.00133 **
## RESP_EDUCHGRAD 0.686233 0.268828 2.553 0.01069 *
## RESP_AGE -0.025296 0.008244 -3.068 0.00215 **
## APSI_SCORE 0.085460 0.032839 2.602 0.00926 **
## KVCO_CATEGFUL_AWARE 0.359423 1.250258 0.287 0.77375
## KVCO_CATEGPAR_AWARE -0.529161 1.275755 -0.415 0.67830
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 727.84 on 631 degrees of freedom
## Residual deviance: 689.53 on 625 degrees of freedom
## AIC: 703.53
##
## Number of Fisher Scoring iterations: 4
######################################
# COMPARING THE MODELS
######################################
formula(KA.df.KVAM.backwardelimination)
## KVAM ~ KVCO_CATEG + APSI_SCORE + RESP_AGE + RESP_EDUC
formula(KA.df.KVAM.forwardselection)
## KVAM ~ RESP_EDUC + RESP_AGE + APSI_SCORE + KVCO_CATEG
formula(KA.df.KVAM.stepwiseregression)
## KVAM ~ RESP_EDUC + RESP_AGE + APSI_SCORE + KVCO_CATEG
######################################
# OBTAINING THE MODEL COEFFICIENTS
######################################
coef(summary(KA.df.KVAM.backwardelimination))[,'Pr(>|z|)']
## (Intercept) KVCO_CATEGFUL_AWARE KVCO_CATEGPAR_AWARE
## 0.566962533 0.773745462 0.678301065
## APSI_SCORE RESP_AGE RESP_EDUCCGRAD_ABOVE
## 0.009257538 0.002152111 0.001325499
## RESP_EDUCHGRAD
## 0.010689745
coef(summary(KA.df.KVAM.forwardselection))[,'Pr(>|z|)']
## (Intercept) RESP_EDUCCGRAD_ABOVE RESP_EDUCHGRAD
## 0.566962533 0.001325499 0.010689745
## RESP_AGE APSI_SCORE KVCO_CATEGFUL_AWARE
## 0.002152111 0.009257538 0.773745462
## KVCO_CATEGPAR_AWARE
## 0.678301065
coef(summary(KA.df.KVAM.stepwiseregression))[,'Pr(>|z|)']
## (Intercept) RESP_EDUCCGRAD_ABOVE RESP_EDUCHGRAD
## 0.566962533 0.001325499 0.010689745
## RESP_AGE APSI_SCORE KVCO_CATEGFUL_AWARE
## 0.002152111 0.009257538 0.773745462
## KVCO_CATEGPAR_AWARE
## 0.678301065
######################################
# OBTAINING THE DEVIANCE
######################################
KA.df.KVAM.backwardelimination$deviance
## [1] 689.5267
KA.df.KVAM.forwardselection$deviance
## [1] 689.5267
KA.df.KVAM.stepwiseregression$deviance
## [1] 689.5267
######################################
# OBTAINING THE AIC
######################################
KA.df.KVAM.backwardelimination$aic
## [1] 703.5267
KA.df.KVAM.forwardselection$aic
## [1] 703.5267
KA.df.KVAM.stepwiseregression$aic
## [1] 703.5267
######################################
# CHALLENGE IS TO CREATE A MODEL WITH AIC CLOSE TO 704
# BUT WITH MORE SIGNIFICANT INDEPENDENT VARIABLES
# PROVIDING BETTER CONTEXT TO THE DEPENDENT VARIABLE
# STEP 1: REVIEW DESCRIPTIVE STATS TO SELECT VARIABLES
# STEP 2: RUN THE MODEL
# STEP 3: DRINK COFFEE
# STEP 4: EVALUATE THE RESULTS
# STEP 5: GO BACK TO STEP 1 IF UNHAPPY WITH THE RESULTS
######################################
######################################
# RERUNNING THE FINAL MODEL WITH
# THE MOST IMPORTANT VARIABLES BASED
# FROM THE MANUAL EVALUATION
######################################
KA.df.KVAM.finalmodel1 <- glm(KVAM ~ APSI_SCORE +
RESP_EDUC +
RESP_AGE,
family = binomial(link = 'logit'),
data=KA.df)
formula(KA.df.KVAM.finalmodel1)
## KVAM ~ APSI_SCORE + RESP_EDUC + RESP_AGE
summary(KA.df.KVAM.finalmodel1)
##
## Call:
## glm(formula = KVAM ~ APSI_SCORE + RESP_EDUC + RESP_AGE, family = binomial(link = "logit"),
## data = KA.df)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.0314 -1.0563 0.6689 0.7818 1.2946
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.706900 0.813130 -0.869 0.384652
## APSI_SCORE 0.083619 0.032409 2.580 0.009878 **
## RESP_EDUCCGRAD_ABOVE 1.132113 0.296350 3.820 0.000133 ***
## RESP_EDUCHGRAD 0.778881 0.264141 2.949 0.003191 **
## RESP_AGE -0.023994 0.008221 -2.919 0.003514 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 727.84 on 631 degrees of freedom
## Residual deviance: 697.56 on 627 degrees of freedom
## AIC: 707.56
##
## Number of Fisher Scoring iterations: 4
exp(coef(KA.df.KVAM.finalmodel1))
## (Intercept) APSI_SCORE RESP_EDUCCGRAD_ABOVE
## 0.4931707 1.0872140 3.1022044
## RESP_EDUCHGRAD RESP_AGE
## 2.1790332 0.9762918
vif(KA.df.KVAM.finalmodel1)
## GVIF Df GVIF^(1/(2*Df))
## APSI_SCORE 1.004337 1 1.002166
## RESP_EDUC 1.006093 2 1.001520
## RESP_AGE 1.003957 1 1.001976
KA.df.KVAM.finalmodel2 <- glm(KVAM ~ APSI_SCORE +
RESP_EDUC +
RESP_AGE +
KLAP_PERCT,
family = binomial(link = 'logit'),
data=KA.df)
formula(KA.df.KVAM.finalmodel2)
## KVAM ~ APSI_SCORE + RESP_EDUC + RESP_AGE + KLAP_PERCT
summary(KA.df.KVAM.finalmodel2)
##
## Call:
## glm(formula = KVAM ~ APSI_SCORE + RESP_EDUC + RESP_AGE + KLAP_PERCT,
## family = binomial(link = "logit"), data = KA.df)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.0578 -1.1003 0.6619 0.7899 1.4007
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.996219 0.832577 -1.197 0.231483
## APSI_SCORE 0.080026 0.032584 2.456 0.014051 *
## RESP_EDUCCGRAD_ABOVE 1.071056 0.298436 3.589 0.000332 ***
## RESP_EDUCHGRAD 0.729331 0.265481 2.747 0.006010 **
## RESP_AGE -0.024735 0.008258 -2.995 0.002741 **
## KLAP_PERCT 0.007959 0.004471 1.780 0.075073 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 727.84 on 631 degrees of freedom
## Residual deviance: 694.39 on 626 degrees of freedom
## AIC: 706.39
##
## Number of Fisher Scoring iterations: 4
exp(coef(KA.df.KVAM.finalmodel2))
## (Intercept) APSI_SCORE RESP_EDUCCGRAD_ABOVE
## 0.3692732 1.0833151 2.9184601
## RESP_EDUCHGRAD RESP_AGE KLAP_PERCT
## 2.0736923 0.9755687 1.0079903
vif(KA.df.KVAM.finalmodel2)
## GVIF Df GVIF^(1/(2*Df))
## APSI_SCORE 1.007636 1 1.003811
## RESP_EDUC 1.018408 2 1.004571
## RESP_AGE 1.007637 1 1.003811
## KLAP_PERCT 1.017834 1 1.008878
######################################
# TESTING MODEL FIT
######################################
######################################
# COMPUTING FOR THE DEVIANCE
######################################
1 - pchisq(KA.df.KVAM.finalmodel2$null.deviance-KA.df.KVAM.finalmodel2$deviance,
KA.df.KVAM.finalmodel2$df.null-KA.df.KVAM.finalmodel2$df.residual)
## [1] 3.070329e-06
######################################
# COMPUTING FOR THE ROC AUC
######################################
KA.df.KVAM.finalmodel2.logitProbS <- predict(KA.df.KVAM.finalmodel2,type=c("response"))
KA.df$LOGITPROBS<-KA.df.KVAM.finalmodel2.logitProbS
KA.df.KVAM.finalmodel2.ROC <- roc(KVAM ~ LOGITPROBS, data = KA.df,auc=TRUE,ci=TRUE,plot=TRUE)
KA.df.KVAM.finalmodel2.ROC.AUC <- KA.df.KVAM.finalmodel2.ROC$auc
KA.df.KVAM.finalmodel2.ROC.AUC
## Area under the curve: 0.6373
######################################
# COMPUTING FOR THE SENSITIVITY
# COMPUTING FOR THE SPECIFICITY
# COMPUTING FOR THE PRECISION
# COMPUTING FOR THE ACCURACY
######################################
KA.df.KVAM.finalmodel2.initialProbs <- round(sum(KA.df$KVAM)/length(KA.df$KVAM),5)
KA.df.KVAM.finalmodel2.initialProbs
## [1] 0.73734
Threshold=KA.df.KVAM.finalmodel2.initialProbs
logitPredicted_Values<-ifelse(predict(KA.df.KVAM.finalmodel2,type="response")>Threshold,1,0)
logitActual_Values<-KA.df$KVAM
logitConfusion_Matrix<-table(logitPredicted_Values,logitActual_Values)
logitConfusion_Matrix
## logitActual_Values
## logitPredicted_Values 0 1
## 0 89 170
## 1 77 296
KA.df.KVAM.finalmodel2.Sensitivity <- (logitConfusion_Matrix[2,2])/
sum(logitConfusion_Matrix[1,2],logitConfusion_Matrix[2,2])
KA.df.KVAM.finalmodel2.Specificity <- (logitConfusion_Matrix[1,1])/
sum(logitConfusion_Matrix[1,1],logitConfusion_Matrix[2,1])
KA.df.KVAM.finalmodel2.Precision <- (logitConfusion_Matrix[2,2])/
sum(logitConfusion_Matrix[2,1],logitConfusion_Matrix[2,2])
KA.df.KVAM.finalmodel2.Accuracy <-(logitConfusion_Matrix[1,1]+logitConfusion_Matrix[2,2])/
sum(logitConfusion_Matrix[1,1],logitConfusion_Matrix[1,2],logitConfusion_Matrix[2,1],logitConfusion_Matrix[2,2])
KA.df.KVAM.finalmodel2.Sensitivity
## [1] 0.6351931
KA.df.KVAM.finalmodel2.Specificity
## [1] 0.5361446
KA.df.KVAM.finalmodel2.Precision
## [1] 0.7935657
KA.df.KVAM.finalmodel2.Accuracy
## [1] 0.6091772
######################################
# INTERPRETING MODEL RESULTS
######################################
# Respondents with the following characteristics have been observed to have sufficient knowledge on vaccination, common misconceptions and general disease prevention (KVAM):
# 1. Higher educational level attained
# 2. Favorable perception on the quality of immunization information
# 3. Younger age
# 4. Higher assessment rating in terms of the knowledge and awareness on immunization laws and programs
# All five significant predictor variables collectively represent the aspects of knowledge and awareness, perceptions on immunization and demographics.
# Educational Attainment - College Graduate and Above
# Having a college or a higher degree increases the odds of having sufficient knowledge in vaccination, common misconceptions and general disease prevention by almost 191% holding the rest of the variables constant.
# Educational Attainment - High School Graduate
# Having a high school diploma increases the odds of having sufficient knowledge in vaccination, common misconceptions and general disease prevention by almost 107% holding the rest of the variables constant.
# Perception on the Quality of Immunization Information
# An increased belief towards the information shared by the government regarding immunization increases the odds of having knowledge in vaccination, common misconceptions and general disease prevention by 8% holding the rest of the variables constant.
# Respondent Age in Years
# A 5-year increase in age reduces the odds of having knowledge in vaccination, common misconceptions and general disease prevention by 15% holding the rest of the variables constant.
# Knowledge on Immunization Laws and Programs
# A 10-unit increase in the knowledge towards the various immunization laws and programs increases the odds of having sufficient knowledge in vaccination, common misconceptions and general disease prevention by 8%% holding the rest of the variables constant.
LOGIT MODELING FOR KVPD
######################################
# CREATING THE LOGIT MODEL FOR KVPD
######################################
######################################
# USING THE FULL MODEL
######################################
KA.df.KVPD.logitfullmodel <- glm(KVPD ~ KLAP_PERCT +
KVCO_CATEG +
APVS_SCORE +
APSI_SCORE +
APVT_SCORE +
PDEX_SCORE +
RESP_SEX +
RESP_RELGN +
RESP_RELAT +
RESP_NKIDS +
RESP_HSTAT +
RESP_AGE +
RESP_ISTAT +
RESP_CSTAT +
RESP_ESTAT +
RESP_EDUC +
RESP_MINC +
RESP_HEXP,
family = binomial(link = 'logit'),
data=KA.df)
summary(KA.df.KVPD.logitfullmodel)
##
## Call:
## glm(formula = KVPD ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE +
## APVT_SCORE + PDEX_SCORE + RESP_SEX + RESP_RELGN + RESP_RELAT +
## RESP_NKIDS + RESP_HSTAT + RESP_AGE + RESP_ISTAT + RESP_CSTAT +
## RESP_ESTAT + RESP_EDUC + RESP_MINC + RESP_HEXP, family = binomial(link = "logit"),
## data = KA.df)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.6606 0.2721 0.4563 0.6106 1.5704
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -6.992665 2.511989 -2.784 0.00537 **
## KLAP_PERCT 0.010617 0.005931 1.790 0.07344 .
## KVCO_CATEGFUL_AWARE 2.922612 1.309092 2.233 0.02558 *
## KVCO_CATEGPAR_AWARE 2.781363 1.341071 2.074 0.03808 *
## APVS_SCORE -0.075710 0.060313 -1.255 0.20937
## APSI_SCORE 0.098806 0.041943 2.356 0.01849 *
## APVT_SCORE 0.116703 0.048494 2.407 0.01610 *
## PDEX_SCORE 0.131370 0.093663 1.403 0.16074
## RESP_SEXFEMALE -0.088043 0.930958 -0.095 0.92465
## RESP_RELGNBORNAGAIN 0.578955 0.622384 0.930 0.35226
## RESP_RELGNCATHOLIC 0.551368 0.463407 1.190 0.23412
## RESP_RELGNINC 0.196913 0.552007 0.357 0.72130
## RESP_RELATFATHER -0.916387 0.958232 -0.956 0.33890
## RESP_RELATMOTHER -0.061032 0.449484 -0.136 0.89199
## RESP_NKIDS 0.117566 0.090250 1.303 0.19269
## RESP_HSTAT 0.052083 0.079178 0.658 0.51066
## RESP_AGE -0.002424 0.015736 -0.154 0.87758
## RESP_ISTATFULLIMMUNIZED_SURE 1.207751 0.889664 1.358 0.17461
## RESP_ISTATFULLIMMUNIZED_UNSURE 0.750801 0.861921 0.871 0.38371
## RESP_ISTATPARTIMMUNIZED 0.578684 0.860548 0.672 0.50129
## RESP_CSTATMARRIED 0.320580 0.583974 0.549 0.58303
## RESP_CSTATSINGLE -0.186480 0.630720 -0.296 0.76749
## RESP_ESTATEMPLOYED 0.351867 0.275568 1.277 0.20165
## RESP_EDUCCGRAD_ABOVE 0.364005 0.440364 0.827 0.40846
## RESP_EDUCHGRAD -0.085496 0.361744 -0.236 0.81317
## RESP_MINC10KTO19K 0.032153 0.278485 0.115 0.90808
## RESP_MINC20KTO49K 0.486730 0.375487 1.296 0.19488
## RESP_MINC50K_ABOVE -0.513205 0.407037 -1.261 0.20737
## RESP_HEXP20K_ABOVE 1.314916 1.102759 1.192 0.23311
## RESP_HEXP5KTO19K 0.402302 0.329980 1.219 0.22278
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 561.94 on 631 degrees of freedom
## Residual deviance: 495.60 on 602 degrees of freedom
## AIC: 555.6
##
## Number of Fisher Scoring iterations: 5
exp(coef(KA.df.KVPD.logitfullmodel))
## (Intercept) KLAP_PERCT
## 9.185953e-04 1.010674e+00
## KVCO_CATEGFUL_AWARE KVCO_CATEGPAR_AWARE
## 1.858979e+01 1.614101e+01
## APVS_SCORE APSI_SCORE
## 9.270848e-01 1.103852e+00
## APVT_SCORE PDEX_SCORE
## 1.123786e+00 1.140389e+00
## RESP_SEXFEMALE RESP_RELGNBORNAGAIN
## 9.157216e-01 1.784173e+00
## RESP_RELGNCATHOLIC RESP_RELGNINC
## 1.735625e+00 1.217638e+00
## RESP_RELATFATHER RESP_RELATMOTHER
## 3.999614e-01 9.407932e-01
## RESP_NKIDS RESP_HSTAT
## 1.124756e+00 1.053464e+00
## RESP_AGE RESP_ISTATFULLIMMUNIZED_SURE
## 9.975790e-01 3.345952e+00
## RESP_ISTATFULLIMMUNIZED_UNSURE RESP_ISTATPARTIMMUNIZED
## 2.118697e+00 1.783690e+00
## RESP_CSTATMARRIED RESP_CSTATSINGLE
## 1.377927e+00 8.298751e-01
## RESP_ESTATEMPLOYED RESP_EDUCCGRAD_ABOVE
## 1.421719e+00 1.439082e+00
## RESP_EDUCHGRAD RESP_MINC10KTO19K
## 9.180569e-01 1.032676e+00
## RESP_MINC20KTO49K RESP_MINC50K_ABOVE
## 1.626987e+00 5.985738e-01
## RESP_HEXP20K_ABOVE RESP_HEXP5KTO19K
## 3.724438e+00 1.495262e+00
vif(KA.df.KVPD.logitfullmodel)
## GVIF Df GVIF^(1/(2*Df))
## KLAP_PERCT 1.155444 1 1.074916
## KVCO_CATEG 1.302894 2 1.068384
## APVS_SCORE 1.127193 1 1.061693
## APSI_SCORE 1.114049 1 1.055485
## APVT_SCORE 1.114894 1 1.055886
## PDEX_SCORE 1.049805 1 1.024600
## RESP_SEX 8.118153 1 2.849237
## RESP_RELGN 1.237144 3 1.036104
## RESP_RELAT 14.740403 2 1.959419
## RESP_NKIDS 1.088874 1 1.043491
## RESP_HSTAT 1.091573 1 1.044784
## RESP_AGE 2.298480 1 1.516074
## RESP_ISTAT 1.162927 3 1.025476
## RESP_CSTAT 1.804532 2 1.159021
## RESP_ESTAT 1.362344 1 1.167195
## RESP_EDUC 1.431306 2 1.093788
## RESP_MINC 1.443830 3 1.063129
## RESP_HEXP 1.162534 2 1.038368
######################################
# ZERO MODEL
######################################
KA.df.KVPD.logitzeromodel <- glm(KVPD ~ 1,
family = binomial(link = 'logit'),
data=KA.df)
summary(KA.df.KVPD.logitzeromodel)
##
## Call:
## glm(formula = KVPD ~ 1, family = binomial(link = "logit"), data = KA.df)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.9048 0.5965 0.5965 0.5965 0.5965
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.6363 0.1077 15.19 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 561.94 on 631 degrees of freedom
## Residual deviance: 561.94 on 631 degrees of freedom
## AIC: 563.94
##
## Number of Fisher Scoring iterations: 3
exp(coef(KA.df.KVPD.logitzeromodel))
## (Intercept)
## 5.135922
######################################
# APPLYING BACKWARD ELIMINATION PROCEDURE
######################################
KA.df.KVPD.backwardelimination = step(KA.df.KVPD.logitfullmodel)
## Start: AIC=555.6
## KVPD ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_RELGN + RESP_RELAT + RESP_NKIDS +
## RESP_HSTAT + RESP_AGE + RESP_ISTAT + RESP_CSTAT + RESP_ESTAT +
## RESP_EDUC + RESP_MINC + RESP_HEXP
##
## Df Deviance AIC
## - RESP_RELGN 3 497.60 551.60
## - RESP_RELAT 2 496.60 552.60
## - RESP_SEX 1 495.61 553.61
## - RESP_AGE 1 495.62 553.62
## - RESP_EDUC 2 497.76 553.76
## - RESP_ISTAT 3 499.98 553.98
## - RESP_HSTAT 1 496.02 554.02
## - RESP_MINC 3 500.53 554.53
## - RESP_HEXP 2 498.84 554.84
## - RESP_CSTAT 2 499.03 555.03
## - APVS_SCORE 1 497.18 555.18
## - RESP_ESTAT 1 497.26 555.26
## - RESP_NKIDS 1 497.42 555.42
## <none> 495.60 555.60
## - PDEX_SCORE 1 497.60 555.60
## - KVCO_CATEG 2 500.80 556.80
## - KLAP_PERCT 1 498.82 556.82
## - APSI_SCORE 1 501.17 559.17
## - APVT_SCORE 1 501.52 559.52
##
## Step: AIC=551.6
## KVPD ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_RELAT + RESP_NKIDS + RESP_HSTAT +
## RESP_AGE + RESP_ISTAT + RESP_CSTAT + RESP_ESTAT + RESP_EDUC +
## RESP_MINC + RESP_HEXP
##
## Df Deviance AIC
## - RESP_RELAT 2 498.36 548.36
## - RESP_SEX 1 497.61 549.61
## - RESP_AGE 1 497.63 549.63
## - RESP_HSTAT 1 497.94 549.94
## - RESP_EDUC 2 500.02 550.02
## - RESP_ISTAT 3 502.04 550.04
## - RESP_MINC 3 502.26 550.26
## - RESP_CSTAT 2 500.27 550.27
## - RESP_HEXP 2 500.47 550.47
## - APVS_SCORE 1 498.87 550.87
## - RESP_ESTAT 1 499.06 551.06
## - RESP_NKIDS 1 499.59 551.59
## <none> 497.60 551.60
## - PDEX_SCORE 1 500.00 552.00
## - KVCO_CATEG 2 502.54 552.54
## - KLAP_PERCT 1 501.19 553.19
## - APSI_SCORE 1 503.44 555.44
## - APVT_SCORE 1 503.50 555.50
##
## Step: AIC=548.36
## KVPD ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_NKIDS + RESP_HSTAT + RESP_AGE +
## RESP_ISTAT + RESP_CSTAT + RESP_ESTAT + RESP_EDUC + RESP_MINC +
## RESP_HEXP
##
## Df Deviance AIC
## - RESP_AGE 1 498.36 546.36
## - RESP_HSTAT 1 498.62 546.62
## - RESP_EDUC 2 500.65 546.65
## - RESP_ISTAT 3 502.76 546.76
## - RESP_CSTAT 2 500.80 546.80
## - RESP_MINC 3 503.41 547.41
## - RESP_HEXP 2 501.47 547.47
## - RESP_ESTAT 1 499.53 547.53
## - APVS_SCORE 1 499.60 547.60
## <none> 498.36 548.36
## - RESP_NKIDS 1 500.47 548.47
## - RESP_SEX 1 500.60 548.60
## - PDEX_SCORE 1 500.84 548.84
## - KVCO_CATEG 2 503.41 549.41
## - KLAP_PERCT 1 502.07 550.07
## - APSI_SCORE 1 504.19 552.19
## - APVT_SCORE 1 504.38 552.38
##
## Step: AIC=546.36
## KVPD ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_NKIDS + RESP_HSTAT + RESP_ISTAT +
## RESP_CSTAT + RESP_ESTAT + RESP_EDUC + RESP_MINC + RESP_HEXP
##
## Df Deviance AIC
## - RESP_HSTAT 1 498.62 544.62
## - RESP_EDUC 2 500.65 544.65
## - RESP_ISTAT 3 502.77 544.77
## - RESP_CSTAT 2 501.23 545.23
## - RESP_MINC 3 503.47 545.47
## - RESP_HEXP 2 501.47 545.47
## - RESP_ESTAT 1 499.53 545.53
## - APVS_SCORE 1 499.60 545.60
## <none> 498.36 546.36
## - RESP_NKIDS 1 500.48 546.48
## - RESP_SEX 1 500.60 546.60
## - PDEX_SCORE 1 500.86 546.86
## - KVCO_CATEG 2 503.42 547.42
## - KLAP_PERCT 1 502.07 548.07
## - APSI_SCORE 1 504.19 550.19
## - APVT_SCORE 1 504.38 550.38
##
## Step: AIC=544.62
## KVPD ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_NKIDS + RESP_ISTAT + RESP_CSTAT +
## RESP_ESTAT + RESP_EDUC + RESP_MINC + RESP_HEXP
##
## Df Deviance AIC
## - RESP_EDUC 2 500.91 542.91
## - RESP_ISTAT 3 502.94 542.94
## - RESP_CSTAT 2 501.47 543.47
## - RESP_HEXP 2 501.65 543.65
## - RESP_MINC 3 503.66 543.66
## - RESP_ESTAT 1 499.82 543.82
## - APVS_SCORE 1 499.90 543.90
## <none> 498.62 544.62
## - RESP_NKIDS 1 500.81 544.81
## - RESP_SEX 1 501.04 545.04
## - PDEX_SCORE 1 501.07 545.07
## - KVCO_CATEG 2 503.55 545.55
## - KLAP_PERCT 1 502.45 546.45
## - APSI_SCORE 1 504.44 548.44
## - APVT_SCORE 1 504.60 548.60
##
## Step: AIC=542.91
## KVPD ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_NKIDS + RESP_ISTAT + RESP_CSTAT +
## RESP_ESTAT + RESP_MINC + RESP_HEXP
##
## Df Deviance AIC
## - RESP_ISTAT 3 505.02 541.02
## - RESP_MINC 3 506.02 542.02
## - RESP_CSTAT 2 504.07 542.07
## - APVS_SCORE 1 502.49 542.49
## - RESP_HEXP 2 504.50 542.50
## - RESP_NKIDS 1 502.88 542.88
## - RESP_ESTAT 1 502.89 542.89
## <none> 500.91 542.91
## - PDEX_SCORE 1 503.34 543.34
## - RESP_SEX 1 503.52 543.52
## - KVCO_CATEG 2 505.77 543.77
## - KLAP_PERCT 1 504.92 544.92
## - APVT_SCORE 1 506.45 546.45
## - APSI_SCORE 1 506.62 546.62
##
## Step: AIC=541.02
## KVPD ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_NKIDS + RESP_CSTAT + RESP_ESTAT +
## RESP_MINC + RESP_HEXP
##
## Df Deviance AIC
## - RESP_MINC 3 510.06 540.06
## - RESP_CSTAT 2 508.37 540.37
## - RESP_HEXP 2 508.58 540.58
## - APVS_SCORE 1 506.69 540.69
## - RESP_ESTAT 1 506.80 540.80
## - RESP_NKIDS 1 506.93 540.93
## <none> 505.02 541.02
## - PDEX_SCORE 1 507.36 541.36
## - RESP_SEX 1 507.76 541.76
## - KVCO_CATEG 2 510.28 542.28
## - KLAP_PERCT 1 509.14 543.14
## - APSI_SCORE 1 510.60 544.60
## - APVT_SCORE 1 511.20 545.20
##
## Step: AIC=540.06
## KVPD ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_NKIDS + RESP_CSTAT + RESP_ESTAT +
## RESP_HEXP
##
## Df Deviance AIC
## - RESP_NKIDS 1 511.29 539.29
## - RESP_HEXP 2 513.52 539.52
## - APVS_SCORE 1 511.64 539.64
## - RESP_CSTAT 2 513.96 539.96
## <none> 510.06 540.06
## - KVCO_CATEG 2 515.00 541.00
## - RESP_ESTAT 1 513.03 541.03
## - PDEX_SCORE 1 513.13 541.13
## - RESP_SEX 1 513.59 541.59
## - KLAP_PERCT 1 514.58 542.58
## - APSI_SCORE 1 515.20 543.20
## - APVT_SCORE 1 516.61 544.61
##
## Step: AIC=539.29
## KVPD ~ KLAP_PERCT + KVCO_CATEG + APVS_SCORE + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_CSTAT + RESP_ESTAT + RESP_HEXP
##
## Df Deviance AIC
## - APVS_SCORE 1 512.75 538.75
## - RESP_HEXP 2 514.90 538.90
## - RESP_CSTAT 2 515.11 539.11
## <none> 511.29 539.29
## - KVCO_CATEG 2 516.06 540.06
## - RESP_ESTAT 1 514.37 540.37
## - PDEX_SCORE 1 514.58 540.58
## - RESP_SEX 1 515.08 541.08
## - APSI_SCORE 1 516.11 542.11
## - KLAP_PERCT 1 516.17 542.17
## - APVT_SCORE 1 517.94 543.94
##
## Step: AIC=538.75
## KVPD ~ KLAP_PERCT + KVCO_CATEG + APSI_SCORE + APVT_SCORE + PDEX_SCORE +
## RESP_SEX + RESP_CSTAT + RESP_ESTAT + RESP_HEXP
##
## Df Deviance AIC
## - RESP_HEXP 2 516.35 538.35
## <none> 512.75 538.75
## - RESP_CSTAT 2 516.92 538.92
## - KVCO_CATEG 2 518.00 540.00
## - PDEX_SCORE 1 516.18 540.18
## - RESP_ESTAT 1 516.19 540.19
## - RESP_SEX 1 516.36 540.36
## - APSI_SCORE 1 517.00 541.00
## - KLAP_PERCT 1 517.50 541.50
## - APVT_SCORE 1 518.93 542.93
##
## Step: AIC=538.35
## KVPD ~ KLAP_PERCT + KVCO_CATEG + APSI_SCORE + APVT_SCORE + PDEX_SCORE +
## RESP_SEX + RESP_CSTAT + RESP_ESTAT
##
## Df Deviance AIC
## <none> 516.35 538.35
## - RESP_CSTAT 2 520.86 538.86
## - RESP_SEX 1 519.72 539.72
## - KVCO_CATEG 2 521.85 539.85
## - PDEX_SCORE 1 519.90 539.90
## - RESP_ESTAT 1 520.26 540.26
## - APSI_SCORE 1 520.57 540.57
## - KLAP_PERCT 1 521.44 541.44
## - APVT_SCORE 1 522.99 542.99
summary(KA.df.KVPD.backwardelimination)
##
## Call:
## glm(formula = KVPD ~ KLAP_PERCT + KVCO_CATEG + APSI_SCORE + APVT_SCORE +
## PDEX_SCORE + RESP_SEX + RESP_CSTAT + RESP_ESTAT, family = binomial(link = "logit"),
## data = KA.df)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.5045 0.3492 0.4812 0.6364 1.6074
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -6.164502 1.816228 -3.394 0.000688 ***
## KLAP_PERCT 0.012720 0.005658 2.248 0.024561 *
## KVCO_CATEGFUL_AWARE 2.758216 1.281624 2.152 0.031387 *
## KVCO_CATEGPAR_AWARE 2.421035 1.315751 1.840 0.065762 .
## APSI_SCORE 0.082112 0.039943 2.056 0.039808 *
## APVT_SCORE 0.119042 0.046635 2.553 0.010690 *
## PDEX_SCORE 0.170266 0.091575 1.859 0.062983 .
## RESP_SEXFEMALE 0.669133 0.356417 1.877 0.060465 .
## RESP_CSTATMARRIED 0.317238 0.528740 0.600 0.548515
## RESP_CSTATSINGLE -0.181756 0.527568 -0.345 0.730458
## RESP_ESTATEMPLOYED 0.498148 0.256020 1.946 0.051687 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 561.94 on 631 degrees of freedom
## Residual deviance: 516.35 on 621 degrees of freedom
## AIC: 538.35
##
## Number of Fisher Scoring iterations: 5
######################################
# APPLYING FORWARD SELECTION PROCEDURE
######################################
KA.df.KVPD.forwardselection = step(KA.df.KVPD.logitzeromodel,
scope=list(lower=formula(KA.df.KVPD.logitzeromodel),
upper=formula(KA.df.KVPD.logitfullmodel)),
direction="forward")
## Start: AIC=563.94
## KVPD ~ 1
##
## Df Deviance AIC
## + KLAP_PERCT 1 546.68 550.68
## + APVT_SCORE 1 551.78 555.78
## + KVCO_CATEG 2 553.46 559.46
## + APSI_SCORE 1 555.48 559.48
## + PDEX_SCORE 1 557.44 561.44
## + RESP_HEXP 2 555.69 561.69
## + RESP_MINC 3 553.85 561.85
## + RESP_SEX 1 558.59 562.59
## + RESP_ISTAT 3 554.71 562.71
## + RESP_EDUC 2 556.71 562.71
## + RESP_ESTAT 1 559.28 563.28
## + RESP_CSTAT 2 557.32 563.32
## + RESP_RELAT 2 557.45 563.45
## <none> 561.94 563.94
## + RESP_NKIDS 1 560.22 564.22
## + APVS_SCORE 1 560.80 564.80
## + RESP_AGE 1 561.34 565.34
## + RESP_HSTAT 1 561.55 565.55
## + RESP_RELGN 3 560.96 568.96
##
## Step: AIC=550.68
## KVPD ~ KLAP_PERCT
##
## Df Deviance AIC
## + APVT_SCORE 1 539.62 545.62
## + APSI_SCORE 1 541.48 547.48
## + PDEX_SCORE 1 542.69 548.69
## + RESP_HEXP 2 541.36 549.36
## + RESP_CSTAT 2 541.80 549.80
## + KVCO_CATEG 2 542.37 550.37
## + RESP_ESTAT 1 544.46 550.46
## + RESP_MINC 3 540.48 550.48
## + RESP_EDUC 2 542.60 550.60
## <none> 546.68 550.68
## + RESP_ISTAT 3 540.70 550.70
## + APVS_SCORE 1 545.41 551.41
## + RESP_SEX 1 545.54 551.54
## + RESP_NKIDS 1 545.57 551.57
## + RESP_AGE 1 546.21 552.21
## + RESP_HSTAT 1 546.53 552.53
## + RESP_RELAT 2 544.67 552.67
## + RESP_RELGN 3 545.97 555.97
##
## Step: AIC=545.62
## KVPD ~ KLAP_PERCT + APVT_SCORE
##
## Df Deviance AIC
## + PDEX_SCORE 1 535.13 543.13
## + RESP_EDUC 2 534.34 544.34
## + APSI_SCORE 1 536.36 544.36
## + RESP_CSTAT 2 534.45 544.45
## + RESP_MINC 3 532.88 544.88
## + KVCO_CATEG 2 534.92 544.92
## + RESP_HEXP 2 535.00 545.00
## + RESP_ESTAT 1 537.30 545.30
## <none> 539.62 545.62
## + APVS_SCORE 1 537.69 545.69
## + RESP_SEX 1 538.23 546.23
## + RESP_ISTAT 3 534.44 546.44
## + RESP_NKIDS 1 538.50 546.50
## + RESP_AGE 1 539.02 547.02
## + RESP_HSTAT 1 539.46 547.46
## + RESP_RELAT 2 537.57 547.57
## + RESP_RELGN 3 538.81 550.81
##
## Step: AIC=543.13
## KVPD ~ KLAP_PERCT + APVT_SCORE + PDEX_SCORE
##
## Df Deviance AIC
## + APSI_SCORE 1 531.71 541.71
## + RESP_EDUC 2 530.00 542.00
## + KVCO_CATEG 2 530.29 542.29
## + RESP_HEXP 2 530.78 542.78
## + RESP_CSTAT 2 530.83 542.83
## <none> 535.13 543.13
## + RESP_ESTAT 1 533.21 543.21
## + APVS_SCORE 1 533.38 543.38
## + RESP_MINC 3 529.41 543.41
## + RESP_SEX 1 533.67 543.67
## + RESP_ISTAT 3 530.02 544.02
## + RESP_NKIDS 1 534.23 544.23
## + RESP_AGE 1 534.78 544.78
## + RESP_HSTAT 1 534.93 544.93
## + RESP_RELAT 2 533.12 545.12
## + RESP_RELGN 3 534.41 548.41
##
## Step: AIC=541.71
## KVPD ~ KLAP_PERCT + APVT_SCORE + PDEX_SCORE + APSI_SCORE
##
## Df Deviance AIC
## + KVCO_CATEG 2 525.84 539.84
## + RESP_EDUC 2 526.29 540.29
## + APVS_SCORE 1 528.98 540.98
## + RESP_HEXP 2 527.28 541.28
## + RESP_ESTAT 1 529.31 541.31
## + RESP_MINC 3 525.62 541.62
## + RESP_CSTAT 2 527.69 541.69
## <none> 531.71 541.71
## + RESP_SEX 1 530.51 542.51
## + RESP_NKIDS 1 530.55 542.55
## + RESP_ISTAT 3 526.59 542.59
## + RESP_HSTAT 1 531.41 543.41
## + RESP_AGE 1 531.41 543.41
## + RESP_RELAT 2 530.04 544.04
## + RESP_RELGN 3 531.24 547.24
##
## Step: AIC=539.84
## KVPD ~ KLAP_PERCT + APVT_SCORE + PDEX_SCORE + APSI_SCORE + KVCO_CATEG
##
## Df Deviance AIC
## + RESP_EDUC 2 520.94 538.94
## + RESP_ESTAT 1 523.63 539.63
## + RESP_HEXP 2 521.66 539.66
## + RESP_MINC 3 519.71 539.71
## + RESP_CSTAT 2 521.72 539.72
## + APVS_SCORE 1 523.81 539.81
## <none> 525.84 539.84
## + RESP_NKIDS 1 524.45 540.45
## + RESP_SEX 1 524.82 540.82
## + RESP_ISTAT 3 521.43 541.43
## + RESP_HSTAT 1 525.44 541.44
## + RESP_AGE 1 525.58 541.58
## + RESP_RELAT 2 524.47 542.47
## + RESP_RELGN 3 525.41 545.41
##
## Step: AIC=538.94
## KVPD ~ KLAP_PERCT + APVT_SCORE + PDEX_SCORE + APSI_SCORE + KVCO_CATEG +
## RESP_EDUC
##
## Df Deviance AIC
## <none> 520.94 538.94
## + RESP_NKIDS 1 518.97 538.97
## + RESP_SEX 1 519.33 539.33
## + APVS_SCORE 1 519.69 539.69
## + RESP_CSTAT 2 517.70 539.70
## + RESP_MINC 3 515.76 539.76
## + RESP_ESTAT 1 519.90 539.90
## + RESP_HEXP 2 517.96 539.96
## + RESP_ISTAT 3 516.35 540.35
## + RESP_HSTAT 1 520.65 540.65
## + RESP_RELAT 2 518.77 540.77
## + RESP_AGE 1 520.78 540.78
## + RESP_RELGN 3 520.66 544.66
summary(KA.df.KVPD.forwardselection)
##
## Call:
## glm(formula = KVPD ~ KLAP_PERCT + APVT_SCORE + PDEX_SCORE + APSI_SCORE +
## KVCO_CATEG + RESP_EDUC, family = binomial(link = "logit"),
## data = KA.df)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.5642 0.3526 0.4851 0.6270 1.6210
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -5.402697 1.672168 -3.231 0.00123 **
## KLAP_PERCT 0.014327 0.005507 2.601 0.00928 **
## APVT_SCORE 0.117904 0.046624 2.529 0.01145 *
## PDEX_SCORE 0.192043 0.090572 2.120 0.03398 *
## APSI_SCORE 0.086552 0.039707 2.180 0.02928 *
## KVCO_CATEGFUL_AWARE 2.618630 1.270482 2.061 0.03929 *
## KVCO_CATEGPAR_AWARE 2.205838 1.295115 1.703 0.08853 .
## RESP_EDUCCGRAD_ABOVE 0.465391 0.394196 1.181 0.23776
## RESP_EDUCHGRAD -0.128453 0.340906 -0.377 0.70632
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 561.94 on 631 degrees of freedom
## Residual deviance: 520.94 on 623 degrees of freedom
## AIC: 538.94
##
## Number of Fisher Scoring iterations: 5
######################################
# APPLYING STEPWISE REGRESSION PROCEDURE
######################################
KA.df.KVPD.stepwiseregression = step(KA.df.KVPD.logitzeromodel,
scope=list(lower=formula(KA.df.KVPD.logitzeromodel),
upper=formula(KA.df.KVPD.logitfullmodel)),
direction="both")
## Start: AIC=563.94
## KVPD ~ 1
##
## Df Deviance AIC
## + KLAP_PERCT 1 546.68 550.68
## + APVT_SCORE 1 551.78 555.78
## + KVCO_CATEG 2 553.46 559.46
## + APSI_SCORE 1 555.48 559.48
## + PDEX_SCORE 1 557.44 561.44
## + RESP_HEXP 2 555.69 561.69
## + RESP_MINC 3 553.85 561.85
## + RESP_SEX 1 558.59 562.59
## + RESP_ISTAT 3 554.71 562.71
## + RESP_EDUC 2 556.71 562.71
## + RESP_ESTAT 1 559.28 563.28
## + RESP_CSTAT 2 557.32 563.32
## + RESP_RELAT 2 557.45 563.45
## <none> 561.94 563.94
## + RESP_NKIDS 1 560.22 564.22
## + APVS_SCORE 1 560.80 564.80
## + RESP_AGE 1 561.34 565.34
## + RESP_HSTAT 1 561.55 565.55
## + RESP_RELGN 3 560.96 568.96
##
## Step: AIC=550.68
## KVPD ~ KLAP_PERCT
##
## Df Deviance AIC
## + APVT_SCORE 1 539.62 545.62
## + APSI_SCORE 1 541.48 547.48
## + PDEX_SCORE 1 542.69 548.69
## + RESP_HEXP 2 541.36 549.36
## + RESP_CSTAT 2 541.80 549.80
## + KVCO_CATEG 2 542.37 550.37
## + RESP_ESTAT 1 544.46 550.46
## + RESP_MINC 3 540.48 550.48
## + RESP_EDUC 2 542.60 550.60
## <none> 546.68 550.68
## + RESP_ISTAT 3 540.70 550.70
## + APVS_SCORE 1 545.41 551.41
## + RESP_SEX 1 545.54 551.54
## + RESP_NKIDS 1 545.57 551.57
## + RESP_AGE 1 546.21 552.21
## + RESP_HSTAT 1 546.53 552.53
## + RESP_RELAT 2 544.67 552.67
## + RESP_RELGN 3 545.97 555.97
## - KLAP_PERCT 1 561.94 563.94
##
## Step: AIC=545.62
## KVPD ~ KLAP_PERCT + APVT_SCORE
##
## Df Deviance AIC
## + PDEX_SCORE 1 535.13 543.13
## + RESP_EDUC 2 534.34 544.34
## + APSI_SCORE 1 536.36 544.36
## + RESP_CSTAT 2 534.45 544.45
## + RESP_MINC 3 532.88 544.88
## + KVCO_CATEG 2 534.92 544.92
## + RESP_HEXP 2 535.00 545.00
## + RESP_ESTAT 1 537.30 545.30
## <none> 539.62 545.62
## + APVS_SCORE 1 537.69 545.69
## + RESP_SEX 1 538.23 546.23
## + RESP_ISTAT 3 534.44 546.44
## + RESP_NKIDS 1 538.50 546.50
## + RESP_AGE 1 539.02 547.02
## + RESP_HSTAT 1 539.46 547.46
## + RESP_RELAT 2 537.57 547.57
## - APVT_SCORE 1 546.68 550.68
## + RESP_RELGN 3 538.81 550.81
## - KLAP_PERCT 1 551.78 555.78
##
## Step: AIC=543.13
## KVPD ~ KLAP_PERCT + APVT_SCORE + PDEX_SCORE
##
## Df Deviance AIC
## + APSI_SCORE 1 531.71 541.71
## + RESP_EDUC 2 530.00 542.00
## + KVCO_CATEG 2 530.29 542.29
## + RESP_HEXP 2 530.78 542.78
## + RESP_CSTAT 2 530.83 542.83
## <none> 535.13 543.13
## + RESP_ESTAT 1 533.21 543.21
## + APVS_SCORE 1 533.38 543.38
## + RESP_MINC 3 529.41 543.41
## + RESP_SEX 1 533.67 543.67
## + RESP_ISTAT 3 530.02 544.02
## + RESP_NKIDS 1 534.23 544.23
## + RESP_AGE 1 534.78 544.78
## + RESP_HSTAT 1 534.93 544.93
## + RESP_RELAT 2 533.12 545.12
## - PDEX_SCORE 1 539.62 545.62
## + RESP_RELGN 3 534.41 548.41
## - APVT_SCORE 1 542.69 548.69
## - KLAP_PERCT 1 546.60 552.60
##
## Step: AIC=541.71
## KVPD ~ KLAP_PERCT + APVT_SCORE + PDEX_SCORE + APSI_SCORE
##
## Df Deviance AIC
## + KVCO_CATEG 2 525.84 539.84
## + RESP_EDUC 2 526.29 540.29
## + APVS_SCORE 1 528.98 540.98
## + RESP_HEXP 2 527.28 541.28
## + RESP_ESTAT 1 529.31 541.31
## + RESP_MINC 3 525.62 541.62
## + RESP_CSTAT 2 527.69 541.69
## <none> 531.71 541.71
## + RESP_SEX 1 530.51 542.51
## + RESP_NKIDS 1 530.55 542.55
## + RESP_ISTAT 3 526.59 542.59
## - APSI_SCORE 1 535.13 543.13
## + RESP_HSTAT 1 531.41 543.41
## + RESP_AGE 1 531.41 543.41
## + RESP_RELAT 2 530.04 544.04
## - PDEX_SCORE 1 536.36 544.36
## - APVT_SCORE 1 537.13 545.13
## + RESP_RELGN 3 531.24 547.24
## - KLAP_PERCT 1 542.47 550.47
##
## Step: AIC=539.84
## KVPD ~ KLAP_PERCT + APVT_SCORE + PDEX_SCORE + APSI_SCORE + KVCO_CATEG
##
## Df Deviance AIC
## + RESP_EDUC 2 520.94 538.94
## + RESP_ESTAT 1 523.63 539.63
## + RESP_HEXP 2 521.66 539.66
## + RESP_MINC 3 519.71 539.71
## + RESP_CSTAT 2 521.72 539.72
## + APVS_SCORE 1 523.81 539.81
## <none> 525.84 539.84
## + RESP_NKIDS 1 524.45 540.45
## + RESP_SEX 1 524.82 540.82
## + RESP_ISTAT 3 521.43 541.43
## + RESP_HSTAT 1 525.44 541.44
## + RESP_AGE 1 525.58 541.58
## - KVCO_CATEG 2 531.71 541.71
## - APSI_SCORE 1 530.29 542.29
## + RESP_RELAT 2 524.47 542.47
## - PDEX_SCORE 1 530.69 542.69
## - APVT_SCORE 1 531.52 543.52
## - KLAP_PERCT 1 532.89 544.89
## + RESP_RELGN 3 525.41 545.41
##
## Step: AIC=538.94
## KVPD ~ KLAP_PERCT + APVT_SCORE + PDEX_SCORE + APSI_SCORE + KVCO_CATEG +
## RESP_EDUC
##
## Df Deviance AIC
## <none> 520.94 538.94
## + RESP_NKIDS 1 518.97 538.97
## + RESP_SEX 1 519.33 539.33
## + APVS_SCORE 1 519.69 539.69
## + RESP_CSTAT 2 517.70 539.70
## + RESP_MINC 3 515.76 539.76
## - RESP_EDUC 2 525.84 539.84
## + RESP_ESTAT 1 519.90 539.90
## + RESP_HEXP 2 517.96 539.96
## - KVCO_CATEG 2 526.29 540.29
## + RESP_ISTAT 3 516.35 540.35
## + RESP_HSTAT 1 520.65 540.65
## + RESP_RELAT 2 518.77 540.77
## + RESP_AGE 1 520.78 540.78
## - PDEX_SCORE 1 525.58 541.58
## - APSI_SCORE 1 525.69 541.69
## - APVT_SCORE 1 527.47 543.47
## - KLAP_PERCT 1 527.77 543.77
## + RESP_RELGN 3 520.66 544.66
summary(KA.df.KVPD.stepwiseregression )
##
## Call:
## glm(formula = KVPD ~ KLAP_PERCT + APVT_SCORE + PDEX_SCORE + APSI_SCORE +
## KVCO_CATEG + RESP_EDUC, family = binomial(link = "logit"),
## data = KA.df)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.5642 0.3526 0.4851 0.6270 1.6210
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -5.402697 1.672168 -3.231 0.00123 **
## KLAP_PERCT 0.014327 0.005507 2.601 0.00928 **
## APVT_SCORE 0.117904 0.046624 2.529 0.01145 *
## PDEX_SCORE 0.192043 0.090572 2.120 0.03398 *
## APSI_SCORE 0.086552 0.039707 2.180 0.02928 *
## KVCO_CATEGFUL_AWARE 2.618630 1.270482 2.061 0.03929 *
## KVCO_CATEGPAR_AWARE 2.205838 1.295115 1.703 0.08853 .
## RESP_EDUCCGRAD_ABOVE 0.465391 0.394196 1.181 0.23776
## RESP_EDUCHGRAD -0.128453 0.340906 -0.377 0.70632
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 561.94 on 631 degrees of freedom
## Residual deviance: 520.94 on 623 degrees of freedom
## AIC: 538.94
##
## Number of Fisher Scoring iterations: 5
######################################
# COMPARING THE MODELS
######################################
formula(KA.df.KVPD.backwardelimination)
## KVPD ~ KLAP_PERCT + KVCO_CATEG + APSI_SCORE + APVT_SCORE + PDEX_SCORE +
## RESP_SEX + RESP_CSTAT + RESP_ESTAT
formula(KA.df.KVPD.forwardselection)
## KVPD ~ KLAP_PERCT + APVT_SCORE + PDEX_SCORE + APSI_SCORE + KVCO_CATEG +
## RESP_EDUC
formula(KA.df.KVPD.stepwiseregression)
## KVPD ~ KLAP_PERCT + APVT_SCORE + PDEX_SCORE + APSI_SCORE + KVCO_CATEG +
## RESP_EDUC
######################################
# OBTAINING THE MODEL COEFFICIENTS
######################################
coef(summary(KA.df.KVPD.backwardelimination))[,'Pr(>|z|)']
## (Intercept) KLAP_PERCT KVCO_CATEGFUL_AWARE
## 0.0006884851 0.0245614374 0.0313873947
## KVCO_CATEGPAR_AWARE APSI_SCORE APVT_SCORE
## 0.0657622733 0.0398082977 0.0106904543
## PDEX_SCORE RESP_SEXFEMALE RESP_CSTATMARRIED
## 0.0629826511 0.0604651446 0.5485145762
## RESP_CSTATSINGLE RESP_ESTATEMPLOYED
## 0.7304578442 0.0516867827
coef(summary(KA.df.KVPD.forwardselection))[,'Pr(>|z|)']
## (Intercept) KLAP_PERCT APVT_SCORE
## 0.001233776 0.009284196 0.011445143
## PDEX_SCORE APSI_SCORE KVCO_CATEGFUL_AWARE
## 0.033978504 0.029276009 0.039290501
## KVCO_CATEGPAR_AWARE RESP_EDUCCGRAD_ABOVE RESP_EDUCHGRAD
## 0.088531031 0.237758565 0.706322288
coef(summary(KA.df.KVPD.stepwiseregression))[,'Pr(>|z|)']
## (Intercept) KLAP_PERCT APVT_SCORE
## 0.001233776 0.009284196 0.011445143
## PDEX_SCORE APSI_SCORE KVCO_CATEGFUL_AWARE
## 0.033978504 0.029276009 0.039290501
## KVCO_CATEGPAR_AWARE RESP_EDUCCGRAD_ABOVE RESP_EDUCHGRAD
## 0.088531031 0.237758565 0.706322288
######################################
# OBTAINING THE DEVIANCE
######################################
KA.df.KVPD.backwardelimination$deviance
## [1] 516.3477
KA.df.KVPD.forwardselection$deviance
## [1] 520.9374
KA.df.KVPD.stepwiseregression$deviance
## [1] 520.9374
######################################
# OBTAINING THE AIC
######################################
KA.df.KVPD.backwardelimination$aic
## [1] 538.3477
KA.df.KVPD.forwardselection$aic
## [1] 538.9374
KA.df.KVPD.stepwiseregression$aic
## [1] 538.9374
######################################
# CHALLENGE IS TO CREATE A MODEL WITH AIC CLOSE TO 539
# BUT WITH MORE SIGNIFICANT INDEPENDENT VARIABLES
# PROVIDING BETTER CONTEXT TO THE DEPENDENT VARIABLE
# STEP 1: REVIEW DESCRIPTIVE STATS TO SELECT VARIABLES
# STEP 2: RUN THE MODEL
# STEP 3: DRINK COFFEE
# STEP 4: EVALUATE THE RESULTS
# STEP 5: GO BACK TO STEP 1 IF UNHAPPY WITH THE RESULTS
######################################
######################################
# RERUNNING THE FINAL MODEL WITH
# THE MOST IMPORTANT VARIABLES BASED
# FROM THE MANUAL EVALUATION
######################################
KA.df.KVPD.finalmodel1 <- glm(KVPD ~ KVCO_CATEG +
APVT_SCORE +
PDEX_SCORE +
APSI_SCORE +
KLAP_PERCT,
family = binomial(link = 'logit'),
data=KA.df)
formula(KA.df.KVPD.finalmodel1)
## KVPD ~ KVCO_CATEG + APVT_SCORE + PDEX_SCORE + APSI_SCORE + KLAP_PERCT
summary(KA.df.KVPD.finalmodel1)
##
## Call:
## glm(formula = KVPD ~ KVCO_CATEG + APVT_SCORE + PDEX_SCORE + APSI_SCORE +
## KLAP_PERCT, family = binomial(link = "logit"), data = KA.df)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.3914 0.3820 0.5003 0.6218 1.5411
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -5.049597 1.651280 -3.058 0.00223 **
## KVCO_CATEGFUL_AWARE 2.482330 1.253289 1.981 0.04763 *
## KVCO_CATEGPAR_AWARE 1.962722 1.280363 1.533 0.12529
## APVT_SCORE 0.108274 0.045837 2.362 0.01817 *
## PDEX_SCORE 0.195598 0.090329 2.165 0.03036 *
## APSI_SCORE 0.083430 0.039528 2.111 0.03480 *
## KLAP_PERCT 0.014431 0.005464 2.641 0.00826 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 561.94 on 631 degrees of freedom
## Residual deviance: 525.84 on 625 degrees of freedom
## AIC: 539.84
##
## Number of Fisher Scoring iterations: 4
exp(coef(KA.df.KVPD.finalmodel1))
## (Intercept) KVCO_CATEGFUL_AWARE KVCO_CATEGPAR_AWARE
## 0.006411916 11.969119295 7.118679943
## APVT_SCORE PDEX_SCORE APSI_SCORE
## 1.114353158 1.216038323 1.087008661
## KLAP_PERCT
## 1.014535446
vif(KA.df.KVPD.finalmodel1)
## GVIF Df GVIF^(1/(2*Df))
## KVCO_CATEG 1.082207 2 1.019947
## APVT_SCORE 1.058002 1 1.028592
## PDEX_SCORE 1.005832 1 1.002912
## APSI_SCORE 1.055954 1 1.027596
## KLAP_PERCT 1.080567 1 1.039503
KA.df.KVPD.finalmodel2 <- glm(KVPD ~ KVCO_CATEG +
APVT_SCORE +
PDEX_SCORE +
APSI_SCORE,
family = binomial(link = 'logit'),
data=KA.df)
formula(KA.df.KVPD.finalmodel2)
## KVPD ~ KVCO_CATEG + APVT_SCORE + PDEX_SCORE + APSI_SCORE
summary(KA.df.KVPD.finalmodel2)
##
## Call:
## glm(formula = KVPD ~ KVCO_CATEG + APVT_SCORE + PDEX_SCORE + APSI_SCORE,
## family = binomial(link = "logit"), data = KA.df)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.3005 0.3984 0.5153 0.6302 1.3693
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -5.04764 1.65110 -3.057 0.00223 **
## KVCO_CATEGFUL_AWARE 2.94991 1.24685 2.366 0.01799 *
## KVCO_CATEGPAR_AWARE 2.22114 1.28062 1.734 0.08284 .
## APVT_SCORE 0.12372 0.04500 2.749 0.00597 **
## PDEX_SCORE 0.20775 0.08981 2.313 0.02071 *
## APSI_SCORE 0.08945 0.03900 2.294 0.02181 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 561.94 on 631 degrees of freedom
## Residual deviance: 532.89 on 626 degrees of freedom
## AIC: 544.89
##
## Number of Fisher Scoring iterations: 4
exp(coef(KA.df.KVPD.finalmodel2))
## (Intercept) KVCO_CATEGFUL_AWARE KVCO_CATEGPAR_AWARE
## 0.006424448 19.104327746 9.217848987
## APVT_SCORE PDEX_SCORE APSI_SCORE
## 1.131701098 1.230904553 1.093574434
vif(KA.df.KVPD.finalmodel2)
## GVIF Df GVIF^(1/(2*Df))
## KVCO_CATEG 1.020254 2 1.005026
## APVT_SCORE 1.038872 1 1.019250
## PDEX_SCORE 1.005774 1 1.002883
## APSI_SCORE 1.052466 1 1.025898
######################################
# TESTING MODEL FIT
######################################
######################################
# COMPUTING FOR THE DEVIANCE
######################################
1 - pchisq(KA.df.KVPD.finalmodel2$null.deviance-KA.df.KVPD.finalmodel2$deviance,
KA.df.KVPD.finalmodel2$df.null-KA.df.KVPD.finalmodel2$df.residual)
## [1] 2.271048e-05
######################################
# COMPUTING FOR THE ROC AUC
######################################
KA.df.KVPD.finalmodel2.logitProbS <- predict(KA.df.KVPD.finalmodel2,type=c("response"))
KA.df$LOGITPROBS<-KA.df.KVPD.finalmodel2.logitProbS
KA.df.KVPD.finalmodel2.ROC <- roc(KVPD ~ LOGITPROBS, data = KA.df,auc=TRUE,ci=TRUE,plot=TRUE)
KA.df.KVPD.finalmodel2.ROC.AUC <- KA.df.KVPD.finalmodel2.ROC$auc
KA.df.KVPD.finalmodel2.ROC.AUC
## Area under the curve: 0.6463
######################################
# COMPUTING FOR THE SENSITIVITY
# COMPUTING FOR THE SPECIFICITY
# COMPUTING FOR THE PRECISION
# COMPUTING FOR THE ACCURACY
######################################
KA.df.KVPD.finalmodel2.initialProbs <- round(sum(KA.df$KVPD)/length(KA.df$KVPD),5)
KA.df.KVPD.finalmodel2.initialProbs
## [1] 0.83703
Threshold=KA.df.KVPD.finalmodel2.initialProbs
logitPredicted_Values<-ifelse(predict(KA.df.KVPD.finalmodel2,type="response")>Threshold,1,0)
logitActual_Values<-KA.df$KVPD
logitConfusion_Matrix<-table(logitPredicted_Values,logitActual_Values)
logitConfusion_Matrix
## logitActual_Values
## logitPredicted_Values 0 1
## 0 59 203
## 1 44 326
KA.df.KVPD.finalmodel2.Sensitivity <- (logitConfusion_Matrix[2,2])/
sum(logitConfusion_Matrix[1,2],logitConfusion_Matrix[2,2])
KA.df.KVPD.finalmodel2.Specificity <- (logitConfusion_Matrix[1,1])/
sum(logitConfusion_Matrix[1,1],logitConfusion_Matrix[2,1])
KA.df.KVPD.finalmodel2.Precision <- (logitConfusion_Matrix[2,2])/
sum(logitConfusion_Matrix[2,1],logitConfusion_Matrix[2,2])
KA.df.KVPD.finalmodel2.Accuracy <-(logitConfusion_Matrix[1,1]+logitConfusion_Matrix[2,2])/
sum(logitConfusion_Matrix[1,1],logitConfusion_Matrix[1,2],logitConfusion_Matrix[2,1],logitConfusion_Matrix[2,2])
KA.df.KVPD.finalmodel2.Sensitivity
## [1] 0.6162571
KA.df.KVPD.finalmodel2.Specificity
## [1] 0.5728155
KA.df.KVPD.finalmodel2.Precision
## [1] 0.8810811
KA.df.KVPD.finalmodel2.Accuracy
## [1] 0.6091772
######################################
# INTERPRETING MODEL RESULTS
######################################
# Respondents with the following characteristics have been observed to have sufficient knowledge on vaccine-preventable diseases (KVPD):
# 1. Higher awareness on controversial issues regarding immunization
# 2. Favorable perception on the quality of immunization information
# 3. Favorable perception on the trustworthiness of the immunization program
# 4. More members of their households have experienced or acquired vaccine-preventable diseases
# All five significant predictor variables collectively represent the aspects of knowledge and awareness, perceptions and practices on immunization.
# Full Awareness on Vaccine Controversies
#Being fully aware of the controversies involving vaccines increases the odds of having sufficient knowledge in vaccine preventable diseases by almost 1,800% holding the rest of the variables constant.
# Partial Awareness on Vaccine Controversies
# Being partially aware of the controversies involving vaccines increases the odds of having sufficient knowledge in vaccine preventable diseases by almost 820% holding the rest of the variables constant.
# Perception on Immunization Program Trustworthiness
# An improved trust towards the government's immunization program increases the odds of having sufficient knowledge in vaccine preventable diseases by almost 13% holding the rest of the variables constant.
# Perception on the Quality of Immunization Information
# A unit increasedin the belief towards the information shared by the government regarding immunization increases the odds of having sufficient knowledge in vaccine preventable diseases by 9% holding the rest of the variables constant.
# Number of Household Members Who Acquired VPDs
# Having a single member of the household experience a vaccine preventable disease increases the odds of having sufficient knowledge about them by 23% holding the rest of the variables constant.