The second of R analysis
MrVinh
12/24/2019
#Descriptive analysis
library(table1)##
## Attaching package: 'table1'## The following objects are masked from 'package:base':
##
## units, units<-library(gapminder)
library(ggplot2)
library(ggthemes)
library(gridExtra)
library(compareGroups)## Loading required package: SNPassoc## Loading required package: haplo.stats## Loading required package: survival## Loading required package: mvtnorm## Loading required package: parallel## Registered S3 method overwritten by 'SNPassoc':
## method from
## summary.haplo.glm haplo.stats#Reading data PISA
t="D:\\R ANALYSIS\\PISA Data Vietnam 2015.csv"
pisa=read.csv(t)
dim(pisa)## [1] 5826 18#Descriptive analysis with table1 and compareGroups
table1(~Region+Area+SchoolType+Math+Read+Science|Area,data=pisa)| REMOTE (n=410) |
RURAL (n=2368) |
URBAN (n=3048) |
Overall (n=5826) |
|
|---|---|---|---|---|
| Region | ||||
| CENTRAL | 198 (48.3%) | 857 (36.2%) | 951 (31.2%) | 2006 (34.4%) |
| NORTH | 148 (36.1%) | 764 (32.3%) | 1046 (34.3%) | 1958 (33.6%) |
| SOUTH | 64 (15.6%) | 747 (31.5%) | 1051 (34.5%) | 1862 (32.0%) |
| Area | ||||
| REMOTE | 410 (100%) | 0 (0%) | 0 (0%) | 410 (7.0%) |
| RURAL | 0 (0%) | 2368 (100%) | 0 (0%) | 2368 (40.6%) |
| URBAN | 0 (0%) | 0 (0%) | 3048 (100%) | 3048 (52.3%) |
| SchoolType | ||||
| Mean (SD) | 3.00 (0.00) | 2.89 (0.464) | 2.80 (0.600) | 2.85 (0.528) |
| Median [Min, Max] | 3.00 [3.00, 3.00] | 3.00 [1.00, 3.00] | 3.00 [1.00, 3.00] | 3.00 [1.00, 3.00] |
| Missing | 0 (0%) | 0 (0%) | 35 (1.1%) | 35 (0.6%) |
| Math | ||||
| Mean (SD) | 450 (82.0) | 500 (81.9) | 499 (79.3) | 496 (81.5) |
| Median [Min, Max] | 446 [216, 696] | 498 [273, 818] | 497 [202, 820] | 493 [202, 820] |
| Read | ||||
| Mean (SD) | 440 (76.0) | 491 (67.6) | 496 (69.6) | 490 (70.6) |
| Median [Min, Max] | 439 [233, 643] | 490 [292, 744] | 495 [107, 718] | 489 [107, 744] |
| Science | ||||
| Mean (SD) | 482 (74.4) | 529 (75.5) | 527 (72.8) | 525 (75.0) |
| Median [Min, Max] | 475 [307, 698] | 529 [335, 807] | 525 [293, 799] | 524 [293, 807] |
temp=compareGroups(Area~PARED+WEALTH+Math+Read+Science,data=pisa)
createTable(temp)##
## --------Summary descriptives table by 'Area'---------
##
## ________________________________________________________
## REMOTE RURAL URBAN p.overall
## N=410 N=2368 N=3048
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
## PARED 7.90 (3.69) 9.38 (3.47) 9.56 (3.48) <0.001
## WEALTH -3.00 (1.25) -2.22 (1.08) -2.12 (1.16) <0.001
## Math 450 (82.0) 500 (81.9) 499 (79.3) <0.001
## Read 440 (76.0) 491 (67.6) 496 (69.6) <0.001
## Science 482 (74.4) 529 (75.5) 527 (72.8) <0.001
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯#Histogram
p3=ggplot(data=pisa,aes(x=Math,fill=Gender))
p3=p3+geom_histogram(position="dodge")
p3+labs(x="Math Score",y="Number of students")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
#Barplot - Part1
p=ggplot(data=pisa,aes(x=Area,fill=Area,col=Area))
p+geom_bar(position="dodge")
#Barplot - Part2
p=ggplot(data=pisa,aes(x=Gender,fill=Area,col=Area))
p+geom_bar(position="stack")
#Boxplot - Part1
p=ggplot(data=pisa,aes(x=Gender,y=Math,fill=Gender))
p+geom_boxplot()
#Boxplot - Part2
p=ggplot(data=pisa,aes(x=Gender,y=Math,fill=Gender))
p+geom_boxplot()+facet_grid(~Area)
#Scatter plot - Part1
p=ggplot(data=pisa,aes(x=WEALTH,y=Math,fill=Gender))
p+geom_point()## Warning: Removed 15 rows containing missing values (geom_point).
#Scatter plot - Part2
p=ggplot(data=pisa,aes(x=WEALTH,y=Math,fill=Gender))
p+geom_point()+geom_smooth(method="lm",se=F)## Warning: Removed 15 rows containing non-finite values (stat_smooth).## Warning: Removed 15 rows containing missing values (geom_point).
#Scatter plot - Part3
p=ggplot(data=pisa,aes(x=WEALTH,y=Science,col=Area))
p+geom_point()+geom_smooth(method="lm",se=F)## Warning: Removed 15 rows containing non-finite values (stat_smooth).## Warning: Removed 15 rows containing missing values (geom_point).
#Multivariable correlation
library(GGally)## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2dat=pisa[,c("Area","Math","Science","Read")]
ggpairs(data=dat,mapping=aes(color=Area))## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
#Multivariable correlation _Part2
library(GGally)
dat=pisa[,c("Area","Math","Science","Read","WEALTH")]
ggpairs(data=dat,mapping=aes(color=Area))## Warning: Removed 15 rows containing non-finite values (stat_boxplot).## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## Warning in (function (data, mapping, alignPercent = 0.6, method = "pearson", :
## Removed 15 rows containing missing values## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## Warning in (function (data, mapping, alignPercent = 0.6, method = "pearson", :
## Removed 15 rows containing missing values## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## Warning in (function (data, mapping, alignPercent = 0.6, method = "pearson", :
## Removed 15 rows containing missing values## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## Warning: Removed 15 rows containing non-finite values (stat_bin).## Warning: Removed 15 rows containing missing values (geom_point).
## Warning: Removed 15 rows containing missing values (geom_point).
## Warning: Removed 15 rows containing missing values (geom_point).## Warning: Removed 15 rows containing non-finite values (stat_density).