Text book: Linear Models with R, 2nd, Julian J. Faraway

1.2 Initional Data Analysis

Package faraway 裡面收集了這本書用到的資料。

#install.packages("faraway")
library(faraway)
## Warning: 套件 'faraway' 是用 R 版本 4.3.1 來建造的
data(pima)
? pima
## 開啟 httpd 求助伺服器… 好了

資料 pima:

Description: The National Institute of Diabetes and Digestive and Kidney Diseases conducted a study on 768 adult female Pima Indians living near Phoenix.

Format: The dataset contains the following variables

  1. pregnant: Number of times pregnant

  2. glucose: Plasma glucose concentration at 2 hours in an oral glucose tolerance test

  3. diastolic: Diastolic blood pressure (mm Hg)

  4. triceps: Triceps skin fold thickness (mm)

  5. insulin: 2-Hour serum insulin (mu U/ml)

  6. bmi: Body mass index (weight in kg/(height in metres squared))

  7. diabetes: Diabetes pedigree function

  8. age: Age (years)

  9. test: test whether the patient shows signs of diabetes (coded 0 if negative, 1 if positive)

-資料整理: missing data, data type

dim(pima)
## [1] 768   9
head(pima) #列出前六筆資料
##   pregnant glucose diastolic triceps insulin  bmi diabetes age test
## 1        6     148        72      35       0 33.6    0.627  50    1
## 2        1      85        66      29       0 26.6    0.351  31    0
## 3        8     183        64       0       0 23.3    0.672  32    1
## 4        1      89        66      23      94 28.1    0.167  21    0
## 5        0     137        40      35     168 43.1    2.288  33    1
## 6        5     116        74       0       0 25.6    0.201  30    0
str(pima)
## 'data.frame':    768 obs. of  9 variables:
##  $ pregnant : int  6 1 8 1 0 5 3 10 2 8 ...
##  $ glucose  : int  148 85 183 89 137 116 78 115 197 125 ...
##  $ diastolic: int  72 66 64 66 40 74 50 0 70 96 ...
##  $ triceps  : int  35 29 0 23 35 0 32 0 45 0 ...
##  $ insulin  : int  0 0 0 94 168 0 88 0 543 0 ...
##  $ bmi      : num  33.6 26.6 23.3 28.1 43.1 25.6 31 35.3 30.5 0 ...
##  $ diabetes : num  0.627 0.351 0.672 0.167 2.288 ...
##  $ age      : int  50 31 32 21 33 30 26 29 53 54 ...
##  $ test     : int  1 0 1 0 1 0 1 0 1 1 ...
summary(pima)
##     pregnant         glucose        diastolic         triceps     
##  Min.   : 0.000   Min.   :  0.0   Min.   :  0.00   Min.   : 0.00  
##  1st Qu.: 1.000   1st Qu.: 99.0   1st Qu.: 62.00   1st Qu.: 0.00  
##  Median : 3.000   Median :117.0   Median : 72.00   Median :23.00  
##  Mean   : 3.845   Mean   :120.9   Mean   : 69.11   Mean   :20.54  
##  3rd Qu.: 6.000   3rd Qu.:140.2   3rd Qu.: 80.00   3rd Qu.:32.00  
##  Max.   :17.000   Max.   :199.0   Max.   :122.00   Max.   :99.00  
##     insulin           bmi           diabetes           age       
##  Min.   :  0.0   Min.   : 0.00   Min.   :0.0780   Min.   :21.00  
##  1st Qu.:  0.0   1st Qu.:27.30   1st Qu.:0.2437   1st Qu.:24.00  
##  Median : 30.5   Median :32.00   Median :0.3725   Median :29.00  
##  Mean   : 79.8   Mean   :31.99   Mean   :0.4719   Mean   :33.24  
##  3rd Qu.:127.2   3rd Qu.:36.60   3rd Qu.:0.6262   3rd Qu.:41.00  
##  Max.   :846.0   Max.   :67.10   Max.   :2.4200   Max.   :81.00  
##       test      
##  Min.   :0.000  
##  1st Qu.:0.000  
##  Median :0.000  
##  Mean   :0.349  
##  3rd Qu.:1.000  
##  Max.   :1.000
head(sort(pima$diastolic),100) #sort() 排序
##   [1]  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0
##  [26]  0  0  0  0  0  0  0  0  0  0 24 30 30 38 40 44 44 44 44 46 46 48 48 48 48
##  [51] 48 50 50 50 50 50 50 50 50 50 50 50 50 50 52 52 52 52 52 52 52 52 52 52 52
##  [76] 54 54 54 54 54 54 54 54 54 54 54 55 55 56 56 56 56 56 56 56 56 56 56 56 56

0 為 missing data，將 missing 的資料改成 NA (Not Available)

pima$diastolic[pima$diastolic==0] <- NA
pima$glucose[pima$glucose==0] <- NA
pima$triceps[pima$triceps==0] <- NA
pima$insulin[pima$insulin==0] <- NA
pima$bmi[pima$bmi==0] <- NA
pima$test <- factor(pima$test)
summary(pima$test)
##   0   1 
## 500 268
levels(pima$test)
## [1] "0" "1"
levels(pima$test) <- c("negative","positive")
summary(pima)
##     pregnant         glucose        diastolic         triceps     
##  Min.   : 0.000   Min.   : 44.0   Min.   : 24.00   Min.   : 7.00  
##  1st Qu.: 1.000   1st Qu.: 99.0   1st Qu.: 64.00   1st Qu.:22.00  
##  Median : 3.000   Median :117.0   Median : 72.00   Median :29.00  
##  Mean   : 3.845   Mean   :121.7   Mean   : 72.41   Mean   :29.15  
##  3rd Qu.: 6.000   3rd Qu.:141.0   3rd Qu.: 80.00   3rd Qu.:36.00  
##  Max.   :17.000   Max.   :199.0   Max.   :122.00   Max.   :99.00  
##                   NA's   :5       NA's   :35       NA's   :227    
##     insulin            bmi           diabetes           age       
##  Min.   : 14.00   Min.   :18.20   Min.   :0.0780   Min.   :21.00  
##  1st Qu.: 76.25   1st Qu.:27.50   1st Qu.:0.2437   1st Qu.:24.00  
##  Median :125.00   Median :32.30   Median :0.3725   Median :29.00  
##  Mean   :155.55   Mean   :32.46   Mean   :0.4719   Mean   :33.24  
##  3rd Qu.:190.00   3rd Qu.:36.60   3rd Qu.:0.6262   3rd Qu.:41.00  
##  Max.   :846.00   Max.   :67.10   Max.   :2.4200   Max.   :81.00  
##  NA's   :374      NA's   :11                                      
##        test    
##  negative:500  
##  positive:268  
##                
##                
##                
##                
##

-Plot

hist(pima$diastolic, xlab="Diastolic",main="") #histogram

plot(density(pima$diastolic, na.rm=TRUE),main="") #pdf

plot(sort(pima$diastolic),ylab="Sorted Diastoic") 

plot(pima$diastolic, pima$diabetes) # scatter plot

boxplot(diabetes~test,pima) #boxplot

plot(diabetes~diastolic, pima) 

plot(diabetes~test,pima)