Loading library

library(table1)
## 
## Attaching package: 'table1'
## The following objects are masked from 'package:base':
## 
##     units, units<-
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:table1':
## 
##     label
## The following object is masked from 'package:base':
## 
##     sort_by
library(ggplot2)

Reading data into R

bw = read.csv("D:\\0. KHOA Y - ĐẠI HỌC VĂN LANG\\11. TÀI LIỆU HỌC\\2. Thầy Tuấn - R\\FILE THỰC HÀNH\\birthwt.csv")

#Listing the first 6 lines
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
#Listing the last 10 lines
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$ethnicity [bw$race==1] ="White"
bw$ethnicity [bw$race==2] ="Black"
bw$ethnicity [bw$race==3] ="Other"

bw$ethnicity = factor(bw$ethnicity, levels = c("White","Other","Black"))

bw$smoking = ifelse(bw$smoke ==1 ,"Smoking","No Smoking")

bw$low.bw = ifelse(bw$low==1 ,"Low BW","No low BW")

bw$mother.wt = bw$lwt*0.45

#Using

table1(~age + ethnicity + smoking + mother.wt+ bwt | low.bw, data=bw )
Low BW
(N=59)
No low BW
(N=130)
Overall
(N=189)
age
Mean (SD) 22.3 (4.51) 23.7 (5.58) 23.2 (5.30)
Median [Min, Max] 22.0 [14.0, 34.0] 23.0 [14.0, 45.0] 23.0 [14.0, 45.0]
ethnicity
White 23 (39.0%) 73 (56.2%) 96 (50.8%)
Other 25 (42.4%) 42 (32.3%) 67 (35.4%)
Black 11 (18.6%) 15 (11.5%) 26 (13.8%)
smoking
No Smoking 29 (49.2%) 86 (66.2%) 115 (60.8%)
Smoking 30 (50.8%) 44 (33.8%) 74 (39.2%)
mother.wt
Mean (SD) 55.0 (12.0) 60.0 (14.3) 58.4 (13.8)
Median [Min, Max] 54.0 [36.0, 90.0] 55.6 [38.3, 113] 54.5 [36.0, 113]
bwt
Mean (SD) 2100 (391) 3330 (478) 2940 (729)
Median [Min, Max] 2210 [709, 2500] 3270 [2520, 4990] 2980 [709, 4990]

#Phân tích bằng biểu đồ dùng lessR

#Phân bố căn nặng của đứa trẻ
Histogram(bwt, data=bw, xlab="cân nặng của trẻ sơ sanh(gram)",ylab="số bà mẹ")

## >>> 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 
## 
#Phân bố chủng tộc
BarChart(ethnicity, 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  Other  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
#Mối liên quan giữa cân nặng của mẹ và con
Plot(lwt, bwt, fit="lm", data=bw)

## 
## 
## >>> Suggestions  or  enter: style(suggest=FALSE)
## Plot(lwt, bwt, enhance=TRUE)  # many options
## Plot(lwt, bwt, fill="skyblue")  # interior fill color of points
## Plot(lwt, bwt, out_cut=.10)  # label top 10% from center as outliers 
## 
## 
## >>> Pearson's product-moment correlation 
##  
## Number of paired values with neither missing, n = 189 
## Sample Correlation of lwt 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 = 4.429    Linear Model MSE = 516,155.173   Rsq = 0.034
##