#Loading library

library(lessR)
## 
## lessR 4.4.3                         feedback: gerbing@pdx.edu 
## --------------------------------------------------------------
## > d <- Read("")  Read data file, many formats available, e.g., Excel
##   d is default data frame, data= in analysis routines optional
## 
## Many examples of reading, writing, and manipulating data, 
## graphics, testing means and proportions, regression, factor analysis,
## customization, forecasting, and aggregation from pivot tables
##   Enter: browseVignettes("lessR")
## 
## View lessR updates, now including time series forecasting
##   Enter: news(package="lessR")
## 
## Interactive data analysis
##   Enter: interact()
## 
## Attaching package: 'lessR'
## The following object is masked from 'package:base':
## 
##     sort_by
library(table1)
## 
## Attaching package: 'table1'
## The following object is masked from 'package:lessR':
## 
##     label
## The following objects are masked from 'package:base':
## 
##     units, units<-
library(ggplot2)

#Reading data into R

#file.choose()
link="D:\\CuDiHoc\\TaiLieuHoc\\ThucHanh\\Data\\birthwt.csv"
bw=read.csv(link)
head(bw)
##   id low age lwt race smoke ptl ht ui ftv  bwt
## 1 85   0  19 182    2     0   0  0  1   0 2523
## 2 86   0  33 155    3     0   0  0  0   3 2551
## 3 87   0  20 105    1     1   0  0  0   1 2557
## 4 88   0  21 108    1     1   0  0  1   2 2594
## 5 89   0  18 107    1     1   0  0  1   0 2600
## 6 91   0  21 124    3     0   0  0  0   0 2622
tail(bw,10)
##     id low age lwt race smoke ptl ht ui ftv  bwt
## 180 71   1  17 120    2     0   0  0  0   2 2438
## 181 75   1  26 154    3     0   1  1  0   1 2442
## 182 76   1  20 105    3     0   0  0  0   3 2450
## 183 77   1  26 190    1     1   0  0  0   0 2466
## 184 78   1  14 101    3     1   1  0  0   0 2466
## 185 79   1  28  95    1     1   0  0  0   2 2466
## 186 81   1  14 100    3     0   0  0  0   2 2495
## 187 82   1  23  94    3     1   0  0  0   0 2495
## 188 83   1  17 142    2     0   0  1  0   0 2495
## 189 84   1  21 130    1     1   0  1  0   3 2495

#Coding data

bw$mwt=bw$lwt*0.453592

bw$ethnicity [bw$race==1] = "White"
bw$ethnicity [bw$race==2] = "Black"
bw$ethnicity [bw$race==3] = "Others"

bw$ethnicity=factor(bw$ethnicity,levels = c("White","Others","Black"))
bw$low.bw=ifelse(bw$low==1,"Low BW","Normal")

head(bw)
##   id low age lwt race smoke ptl ht ui ftv  bwt      mwt ethnicity low.bw
## 1 85   0  19 182    2     0   0  0  1   0 2523 82.55374     Black Normal
## 2 86   0  33 155    3     0   0  0  0   3 2551 70.30676    Others Normal
## 3 87   0  20 105    1     1   0  0  0   1 2557 47.62716     White Normal
## 4 88   0  21 108    1     1   0  0  1   2 2594 48.98794     White Normal
## 5 89   0  18 107    1     1   0  0  1   0 2600 48.53434     White Normal
## 6 91   0  21 124    3     0   0  0  0   0 2622 56.24541    Others Normal
tail(bw,10)
##     id low age lwt race smoke ptl ht ui ftv  bwt      mwt ethnicity low.bw
## 180 71   1  17 120    2     0   0  0  0   2 2438 54.43104     Black Low BW
## 181 75   1  26 154    3     0   1  1  0   1 2442 69.85317    Others Low BW
## 182 76   1  20 105    3     0   0  0  0   3 2450 47.62716    Others Low BW
## 183 77   1  26 190    1     1   0  0  0   0 2466 86.18248     White Low BW
## 184 78   1  14 101    3     1   1  0  0   0 2466 45.81279    Others Low BW
## 185 79   1  28  95    1     1   0  0  0   2 2466 43.09124     White Low BW
## 186 81   1  14 100    3     0   0  0  0   2 2495 45.35920    Others Low BW
## 187 82   1  23  94    3     1   0  0  0   0 2495 42.63765    Others Low BW
## 188 83   1  17 142    2     0   0  1  0   0 2495 64.41006     Black Low BW
## 189 84   1  21 130    1     1   0  1  0   3 2495 58.96696     White Low BW

#Descriptive analysis

bw1=bw[,c("id","low","bwt")]
#bw1=bw[, c(1,2,11)] vị trí biến
#bw1=bw[, c(1,2,8:11)] vị trí biến

dim(bw1)
## [1] 189   3
bw2=subset(bw, low==1)
dim(bw2)
## [1] 59 14
bw3=subset(bw,low==1 & smoke==1)
dim(bw3)
## [1] 30 14
table1(~age+mwt+bwt, data=bw)
Overall
(N=189)
age
Mean (SD) 23.2 (5.30)
Median [Min, Max] 23.0 [14.0, 45.0]
mwt
Mean (SD) 58.9 (13.9)
Median [Min, Max] 54.9 [36.3, 113]
bwt
Mean (SD) 2940 (729)
Median [Min, Max] 2980 [709, 4990] 
bw$smoking=ifelse(bw$smoke==1,"Smoking","Non smoking")
table1(~age+mwt+bwt+ethnicity+smoking|low, data=bw)
0
(N=130)		 1
(N=59)		 Overall
(N=189)
age
Mean (SD) 23.7 (5.58) 22.3 (4.51) 23.2 (5.30)
Median [Min, Max] 23.0 [14.0, 45.0] 22.0 [14.0, 34.0] 23.0 [14.0, 45.0]
mwt
Mean (SD) 60.5 (14.4) 55.4 (12.0) 58.9 (13.9)
Median [Min, Max] 56.0 [38.6, 113] 54.4 [36.3, 90.7] 54.9 [36.3, 113]
bwt
Mean (SD) 3330 (478) 2100 (391) 2940 (729)
Median [Min, Max] 3270 [2520, 4990] 2210 [709, 2500] 2980 [709, 4990]
ethnicity
White 73 (56.2%) 23 (39.0%) 96 (50.8%)
Others 42 (32.3%) 25 (42.4%) 67 (35.4%)
Black 15 (11.5%) 11 (18.6%) 26 (13.8%)
smoking
Non smoking 86 (66.2%) 29 (49.2%) 115 (60.8%)
Smoking 44 (33.8%) 30 (50.8%) 74 (39.2%)

#phan tich bang bieu do

Histogram(bwt,xlab="Cân nặng của trẻ sơ sinh (g)", ylab="Số bà mẹ", data=bw)

## >>> Suggestions 
## bin_width: set the width of each bin 
## bin_start: set the start of the first bin 
## bin_end: set the end of the last bin 
## Histogram(bwt, density=TRUE)  # smoothed curve + histogram 
## Plot(bwt)  # Violin/Box/Scatterplot (VBS) plot 
## 
## --- bwt --- 
##  
##       n   miss       mean         sd        min        mdn        max 
##      189      0    2944.59     729.21     709.00    2977.00    4990.00 
##  
## 
##   
## --- Outliers ---     from the box plot: 1 
##  
## Small        Large 
## -----        ----- 
##  709.0            
## 
## 
## Bin Width: 500 
## Number of Bins: 9 
##  
##          Bin  Midpnt  Count    Prop  Cumul.c  Cumul.p 
## ----------------------------------------------------- 
##   500 > 1000     750      1    0.01        1     0.01 
##  1000 > 1500    1250      4    0.02        5     0.03 
##  1500 > 2000    1750     14    0.07       19     0.10 
##  2000 > 2500    2250     40    0.21       59     0.31 
##  2500 > 3000    2750     38    0.20       97     0.51 
##  3000 > 3500    3250     45    0.24      142     0.75 
##  3500 > 4000    3750     38    0.20      180     0.95 
##  4000 > 4500    4250      7    0.04      187     0.99 
##  4500 > 5000    4750      2    0.01      189     1.00 
## 
BarChart(ethnicity, ylab="Số bà mẹ", data=bw)

## >>> Suggestions
## BarChart(ethnicity, horiz=TRUE)  # horizontal bar chart
## BarChart(ethnicity, fill="reds")  # red bars of varying lightness
## PieChart(ethnicity)  # doughnut (ring) chart
## Plot(ethnicity)  # bubble plot
## Plot(ethnicity, stat="count")  # lollipop plot 
## 
## --- ethnicity --- 
## 
## Missing Values: 0 
## 
##                White  Others  Black     Total 
## Frequencies:      96      67     26       189 
## Proportions:   0.508   0.354  0.138     1.000 
## 
## Chi-squared test of null hypothesis of equal probabilities 
##   Chisq = 39.270, df = 2, p-value = 0.000
Plot(mwt, bwt, xlab="Cân nặng của mẹ", ylab="Cân nặng của con", fit="lm", data=bw)

## 
## 
## >>> Suggestions  or  enter: style(suggest=FALSE)
## Plot(mwt, bwt, enhance=TRUE)  # many options
## Plot(mwt, bwt, color="red")  # exterior edge color of points
## Plot(mwt, bwt, MD_cut=6)  # Mahalanobis distance from center > 6 is an outlier 
## 
## 
## >>> Pearson's product-moment correlation 
##  
## Number of paired values with neither missing, n = 189 
## Sample Correlation of mwt and bwt: r = 0.186 
##   
## Hypothesis Test of 0 Correlation:  t = 2.585,  df = 187,  p-value = 0.011 
## 95% Confidence Interval for Correlation:  0.044 to 0.320 
##   
## 
##   Line: b0 = 2369.624    b1 = 9.765    Linear Model MSE = 516,155.173   Rsq = 0.034
##