Loading the CSV file in RMarkdown
library(readr)
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6 ✔ dplyr 1.0.10
## ✔ tibble 3.1.8 ✔ stringr 1.4.1
## ✔ tidyr 1.2.1 ✔ forcats 0.5.2
## ✔ purrr 0.3.5
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
library(Hmisc)
## Loading required package: lattice
## Loading required package: survival
## Loading required package: Formula
##
## Attaching package: 'Hmisc'
##
## The following objects are masked from 'package:dplyr':
##
## src, summarize
##
## The following objects are masked from 'package:base':
##
## format.pval, units
library(ggplot2)
library(glm2)
##
## Attaching package: 'glm2'
##
## The following object is masked from 'package:survival':
##
## heart
library(knitr)
#Loading the dataset
uphia<-read.csv(file.choose())
Well-labelled summary tables
summary(uphia)
## X personid region gender
## Min. : 1 Length:2893 Min. : 1.000 Length:2893
## 1st Qu.: 724 Class :character 1st Qu.: 4.000 Class :character
## Median :1447 Mode :character Median : 5.000 Mode :character
## Mean :1447 Mean : 5.491
## 3rd Qu.:2170 3rd Qu.: 7.000
## Max. :2893 Max. :10.000
##
## age work12mo occuptn ethnic
## Min. :15.00 Length:2893 Length:2893 Length:2893
## 1st Qu.:20.00 Class :character Class :character Class :character
## Median :29.00 Mode :character Mode :character Mode :character
## Mean :33.19
## 3rd Qu.:42.00
## Max. :80.00
##
## mcstatus firstsxage lifetimesex part12monum
## Length:2893 Min. :14.00 Min. : 1.000 Min. :-7.000
## Class :character 1st Qu.:15.00 1st Qu.: 3.000 1st Qu.: 1.000
## Mode :character Median :17.00 Median : 4.000 Median : 1.000
## Mean :17.17 Mean : 5.773 Mean : 1.033
## 3rd Qu.:18.00 3rd Qu.: 6.000 3rd Qu.: 1.000
## Max. :30.00 Max. :21.000 Max. : 7.000
## NA's :737 NA's :658 NA's :622
## urban wealthquintile hivstatusfinal education
## Length:2893 Length:2893 Length:2893 Length:2893
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## uniontype marital evertested bt_status
## Min. : 1.00 Length:2893 Length:2893 Length:2893
## 1st Qu.: 2.00 Class :character Class :character Class :character
## Median : 3.00 Mode :character Mode :character Mode :character
## Mean :18.01
## 3rd Qu.: 3.00
## Max. :99.00
##
## sex12months sexever condomlastsex12months
## Length:2893 Length:2893 Length:2893
## Class :character Class :character Class :character
## Mode :character Mode :character Mode :character
##
##
##
##
## lastpartnerrelation12months lastpartnerspouselivein12months
## Length:2893 Length:2893
## Class :character Class :character
## Mode :character Mode :character
##
##
##
##
## allpartnersspouselivein12months condomlastnonmaritalsex12months
## Length:2893 Length:2893
## Class :character Class :character
## Mode :character Mode :character
##
##
##
##
hist(uphia$age)
plot(uphia$lifetimesex)
Tables stratified by all variables
table(uphia$gender, uphia$hivstatusfinal)
##
## 99 negative positive
## female 166 1309 104
## male 255 1013 46
table(uphia$region, uphia$hivstatusfinal)
##
## 99 negative positive
## 1 42 182 22
## 2 37 183 19
## 3 35 171 18
## 4 48 257 15
## 5 59 363 22
## 6 53 262 11
## 7 36 336 8
## 8 56 193 12
## 9 26 207 11
## 10 29 168 12
table(uphia$work12mo, uphia$hivstatusfinal)
##
## 99 negative positive
## -9 1 0 0
## no 10 1113 62
## yes 27 1209 88
table(uphia$occuptn, uphia$hivstatusfinal)
##
## 99 negative positive
## agriculture 9 429 27
## clerical 0 3 2
## domestic service 1 64 3
## other specify 2 69 2
## professional/technical/managerial 2 111 4
## sales and services 6 201 20
## skiled manual 1 109 8
## unskilled manual 6 223 22
table(uphia$ethnic, uphia$hivstatusfinal)
##
## 99 negative positive
## 99 383 2 0
## Acholi 4 216 4
## Alur/Jopadhola 0 67 6
## Baganda 9 325 38
## BAgisu/Sabiny 1 47 6
## Bakiga 0 205 10
## Banyankole 1 159 14
## Banyoro 9 577 28
## Basoga 3 217 16
## Iteso 4 214 11
## Karimojong 4 67 7
## Langi 3 135 4
## Lugbara/Madi 0 91 6
table(uphia$mcstatus, uphia$hivstatusfinal)
##
## 99 negative positive
## -8 0 3 0
## no 13 550 34
## yes 11 460 12
table(uphia$urban, uphia$hivstatusfinal)
##
## 99 negative positive
## no 299 1705 90
## yes 122 617 60
table(uphia$part12monum, uphia$hivstatusfinal)
##
## 99 negative positive
## -7 0 3 0
## 0 6 385 40
## 1 16 1393 85
## 2 4 225 14
## 3 2 56 2
## 4 0 16 0
## 5 1 8 2
## 6 0 3 1
## 7 2 5 2
table(uphia$region, uphia$hivstatusfinal)
##
## 99 negative positive
## 1 42 182 22
## 2 37 183 19
## 3 35 171 18
## 4 48 257 15
## 5 59 363 22
## 6 53 262 11
## 7 36 336 8
## 8 56 193 12
## 9 26 207 11
## 10 29 168 12
table(uphia$wealthquintile, uphia$hivstatusfinal)
##
## 99 negative positive
## middle 81 425 32
## poor 96 482 24
## rich 59 370 41
## very poor 107 652 15
## very rich 78 393 38
table(uphia$education, uphia$hivstatusfinal)
##
## 99 negative positive
## 99 383 22 1
## no education 5 194 10
## primary 19 1013 69
## secondary 5 347 21
## tertiary 7 543 40
## university 2 203 9
table(uphia$uniontype, uphia$hivstatusfinal)
##
## 99 negative positive
## 1 4 329 20
## 2 14 923 46
## 3 17 996 74
## 99 386 74 10
table(uphia$marital, uphia$hivstatusfinal)
##
## 99 negative positive
## 99 384 2 1
## divorced 1 77 23
## living together 1 44 10
## married 20 1324 75
## seperated 10 673 17
## widowed 5 202 24
table(uphia$evertested, uphia$hivstatusfinal)
##
## 99 negative positive
## 99 383 8 0
## no 9 554 13
## yes 29 1760 137
table(uphia$bt_status, uphia$hivstatusfinal)
##
## 99 negative positive
## 9 0 55 2
## no 36 0 0
## yes 0 2267 148
table(uphia$sex12months, uphia$hivstatusfinal)
##
## 99 negative positive
## 99 390 304 7
## no 6 309 37
## yes 25 1709 106
table(uphia$sexever, uphia$hivstatusfinal)
##
## 99 negative positive
## 99 383 3 0
## no 5 290 6
## yes 33 2029 144
table(uphia$condomlastsex12months, uphia$hivstatusfinal)
##
## 99 negative positive
## 3 6 309 37
## 99 391 319 9
## no 22 1485 88
## yes 2 209 16
table(uphia$lastpartnerrelation12months, uphia$hivstatusfinal)
##
## 99 negative positive
## 3 3 208 19
## 4 1 47 2
## 5 3 192 10
## 8 0 2 0
## 9 0 2 1
## 96 0 4 0
## 99 397 627 46
## no 1 145 12
## yes 16 1095 60
table(uphia$lastpartnerspouselivein12months, uphia$hivstatusfinal)
##
## 99 negative positive
## 99 397 627 46
## no 7 455 32
## yes 17 1240 72
table(uphia$allpartnersspouselivein12months, uphia$hivstatusfinal)
##
## 99 negative positive
## 99 396 617 44
## no 11 562 39
## yes 14 1143 67
table(uphia$condomlastnonmaritalsex12months, uphia$hivstatusfinal)
##
## 99 negative positive
## 99 410 1766 113
## no 8 383 27
## yes 3 173 10
Assessing Relationships
chisq.test(uphia$hivstatusfinal, uphia$gender)
##
## Pearson's Chi-squared test
##
## data: uphia$hivstatusfinal and uphia$gender
## X-squared = 55.163, df = 2, p-value = 1.051e-12
anova<-aov(uphia$age~uphia$hivstatusfinal)
summary(anova)
## Df Sum Sq Mean Sq F value Pr(>F)
## uphia$hivstatusfinal 2 73481 36741 170.2 <2e-16 ***
## Residuals 2890 623708 216
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova1<-aov(uphia$age~uphia$wealthquintile)
summary(anova1)
## Df Sum Sq Mean Sq F value Pr(>F)
## uphia$wealthquintile 4 4383 1095.6 4.567 0.00112 **
## Residuals 2888 692806 239.9
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova2<-aov(uphia$age~uphia$hivstatusfinal)
summary(anova2)
## Df Sum Sq Mean Sq F value Pr(>F)
## uphia$hivstatusfinal 2 73481 36741 170.2 <2e-16 ***
## Residuals 2890 623708 216
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova3<-aov(uphia$lifetimesex~uphia$condomlastsex12months)
summary(anova3)
## Df Sum Sq Mean Sq F value Pr(>F)
## uphia$condomlastsex12months 3 1289 429.6 26.61 <2e-16 ***
## Residuals 2231 36017 16.1
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 658 observations deleted due to missingness
chisq.test(uphia$education, uphia$urban)
##
## Pearson's Chi-squared test
##
## data: uphia$education and uphia$urban
## X-squared = 157.37, df = 5, p-value < 2.2e-16
chisq.test(uphia$wealthquintile, uphia$urban)
##
## Pearson's Chi-squared test
##
## data: uphia$wealthquintile and uphia$urban
## X-squared = 1209, df = 4, p-value < 2.2e-16
Necessary Plots
boxplot(uphia$age~uphia$hivstatusfinal)
boxplot(uphia$age~uphia$wealthquintile)
boxplot(uphia$lifetimesex~uphia$condomlastsex12months)
boxplot(uphia$lifetimesex~uphia$condomlastnonmaritalsex12months)
END