Gói packages liên quan

library(table1)
## Warning: package 'table1' was built under R version 4.4.3
## 
## Attaching package: 'table1'
## The following objects are masked from 'package:base':
## 
##     units, units<-
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.4.3

Đọc dữ liệu vào R

bw = read.csv("C:/Users/lehoa/Desktop/thuế/học như một NCS/R với thầy Tuấn/birthwt.csv",
               header = TRUE)
dim(bw)
## [1] 189  11
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
bw$mwt = round(bw$lwt*0.453592,2)

Biên tập dữ liệu

bw$ethnicity [bw$race==1]<-"White"
bw$ethnicity [bw$race==2]<-"black"
bw$ethnicity [bw$race==3]<-"other"
head(bw)
##   id low age lwt race smoke ptl ht ui ftv  bwt   mwt ethnicity
## 1 85   0  19 182    2     0   0  0  1   0 2523 82.55     black
## 2 86   0  33 155    3     0   0  0  0   3 2551 70.31     other
## 3 87   0  20 105    1     1   0  0  0   1 2557 47.63     White
## 4 88   0  21 108    1     1   0  0  1   2 2594 48.99     White
## 5 89   0  18 107    1     1   0  0  1   0 2600 48.53     White
## 6 91   0  21 124    3     0   0  0  0   0 2622 56.25     other
bw1 = bw[,c("id","low","bwt")]
bw2=subset(bw,low==1)
bw3 = subset(bw,low==1 & smoke==1)

Phân tích mô tả

library(table1)
table1(~age + lwt + bwt, data=bw)
Overall
(N=189)
age
Mean (SD) 23.2 (5.30)
Median [Min, Max] 23.0 [14.0, 45.0]
lwt
Mean (SD) 130 (30.6)
Median [Min, Max] 121 [80.0, 250]
bwt
Mean (SD) 2940 (729)
Median [Min, Max] 2980 [709, 4990] 
table1(~age + lwt + bwt | low, data=bw)
## Warning in table1.formula(~age + lwt + bwt | low, data = bw): Terms to the
## right of '|' in formula 'x' define table columns and are expected to be factors
## with meaningful labels.
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]
lwt
Mean (SD) 133 (31.7) 122 (26.6) 130 (30.6)
Median [Min, Max] 124 [85.0, 250] 120 [80.0, 200] 121 [80.0, 250]
bwt
Mean (SD) 3330 (478) 2100 (391) 2940 (729)
Median [Min, Max] 3270 [2520, 4990] 2210 [709, 2500] 2980 [709, 4990] 
table1(~factor(smoke) + factor(race) | factor(low), data=bw)
0
(N=130)		 1
(N=59)		 Overall
(N=189)
factor(smoke)
0 86 (66.2%) 29 (49.2%) 115 (60.8%)
1 44 (33.8%) 30 (50.8%) 74 (39.2%)
factor(race)
1 73 (56.2%) 23 (39.0%) 96 (50.8%)
2 15 (11.5%) 11 (18.6%) 26 (13.8%)
3 42 (32.3%) 25 (42.4%) 67 (35.4%) 
bw$smoking = ifelse(bw$smoke==1,"yes","no")

Vẽ biểu đồ

library(lessR)
## Warning: package 'lessR' was built under R version 4.4.3
## 
## 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
Histogram(bwt, 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 
## 
Histogram(bwt, fill="purple", xlab="Cân nặng khi sinh (g)",ylab="Tỉ lệ (%)", 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, 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 
## 
##                black  other  White     Total 
## Frequencies:      26     67     96       189 
## Proportions:   0.138  0.354  0.508     1.000 
## 
## Chi-squared test of null hypothesis of equal probabilities 
##   Chisq = 39.270, df = 2, p-value = 0.000
Plot(lwt, bwt, 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, fit="lm", fit_se=c(.90,.99))  # fit line, stnd errors
## 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 
## 
Plot(lwt, bwt, by=ethnicity, 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 
## 
## ethnicity: black  Line: b0 = 2363.222    b1 = 2.428    Linear Model MSE = 415,263.548   Rsq = 0.023
##  
## ethnicity: other  Line: b0 = 2070.778    b1 = 6.120    Linear Model MSE = 505,570.324   Rsq = 0.045
##  
## ethnicity: White  Line: b0 = 2442.418    b1 = 5.000    Linear Model MSE = 514,065.615   Rsq = 0.040
##