KN3

#install.packages("MASS")  
library(MASS)

## Warning: package 'MASS' was built under R version 4.4.3

data <- Boston  
model <- lm(medv ~ rm, data = data)
summary(model)

## 
## Call:
## lm(formula = medv ~ rm, data = data)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -23.346  -2.547   0.090   2.986  39.433 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept)  -34.671      2.650  -13.08   <2e-16 ***
## rm             9.102      0.419   21.72   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 6.616 on 504 degrees of freedom
## Multiple R-squared:  0.4835, Adjusted R-squared:  0.4825 
## F-statistic: 471.8 on 1 and 504 DF,  p-value: < 2.2e-16

residuals <- residuals(model)
shapiro.test(residuals)

## 
##  Shapiro-Wilk normality test
## 
## data:  residuals
## W = 0.92046, p-value = 1.088e-15

#install.packages("ISLR")  # Cài đặt gói nếu chưa có
library(ISLR)

## Warning: package 'ISLR' was built under R version 4.4.3

data <- Default  # Tải dữ liệu
str(data)  # Kiểm tra kiểu dữ liệu

## 'data.frame':    10000 obs. of  4 variables:
##  $ default: Factor w/ 2 levels "No","Yes": 1 1 1 1 1 1 1 1 1 1 ...
##  $ student: Factor w/ 2 levels "No","Yes": 1 2 1 1 1 2 1 2 1 1 ...
##  $ balance: num  730 817 1074 529 786 ...
##  $ income : num  44362 12106 31767 35704 38463 ...

summary(data)  # Tóm tắt thống kê

##  default    student       balance           income     
##  No :9667   No :7056   Min.   :   0.0   Min.   :  772  
##  Yes: 333   Yes:2944   1st Qu.: 481.7   1st Qu.:21340  
##                        Median : 823.6   Median :34553  
##                        Mean   : 835.4   Mean   :33517  
##                        3rd Qu.:1166.3   3rd Qu.:43808  
##                        Max.   :2654.3   Max.   :73554

data$default <- as.factor(ifelse(data$default == "Yes", 1, 0))  # Chuyển thành nhị phân
model <- glm(default ~ balance + income, data = data, family = binomial)
summary(model)

## 
## Call:
## glm(formula = default ~ balance + income, family = binomial, 
##     data = data)
## 
## Coefficients:
##               Estimate Std. Error z value Pr(>|z|)    
## (Intercept) -1.154e+01  4.348e-01 -26.545  < 2e-16 ***
## balance      5.647e-03  2.274e-04  24.836  < 2e-16 ***
## income       2.081e-05  4.985e-06   4.174 2.99e-05 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 2920.6  on 9999  degrees of freedom
## Residual deviance: 1579.0  on 9997  degrees of freedom
## AIC: 1585
## 
## Number of Fisher Scoring iterations: 8