ktkn3

# Cài và nạp thư viện
library(MASS)

# Nạp dữ liệu
data(Boston)

# Xem qua dữ liệu
head(Boston)

##      crim zn indus chas   nox    rm  age    dis rad tax ptratio  black lstat
## 1 0.00632 18  2.31    0 0.538 6.575 65.2 4.0900   1 296    15.3 396.90  4.98
## 2 0.02731  0  7.07    0 0.469 6.421 78.9 4.9671   2 242    17.8 396.90  9.14
## 3 0.02729  0  7.07    0 0.469 7.185 61.1 4.9671   2 242    17.8 392.83  4.03
## 4 0.03237  0  2.18    0 0.458 6.998 45.8 6.0622   3 222    18.7 394.63  2.94
## 5 0.06905  0  2.18    0 0.458 7.147 54.2 6.0622   3 222    18.7 396.90  5.33
## 6 0.02985  0  2.18    0 0.458 6.430 58.7 6.0622   3 222    18.7 394.12  5.21
##   medv
## 1 24.0
## 2 21.6
## 3 34.7
## 4 33.4
## 5 36.2
## 6 28.7

# Xây dựng mô hình hồi quy tuyến tính
model_lm <- lm(medv ~ rm, data = Boston)

# Kết quả mô hình
summary(model_lm)

## 
## Call:
## lm(formula = medv ~ rm, data = Boston)
## 
## 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

# Lấy residuals
res <- residuals(model_lm)

# Histogram
hist(res, breaks = 20, main = "Histogram of Residuals")

# Q-Q plot
qqnorm(res)
qqline(res, col = "red")

library(ISLR)

data(Default)
str(Default)

## '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 ...

model_logit <- glm(default ~ income + balance + student,
                   data = Default,
                   family = binomial)

summary(model_logit)

## 
## Call:
## glm(formula = default ~ income + balance + student, family = binomial, 
##     data = Default)
## 
## Coefficients:
##               Estimate Std. Error z value Pr(>|z|)    
## (Intercept) -1.087e+01  4.923e-01 -22.080  < 2e-16 ***
## income       3.033e-06  8.203e-06   0.370  0.71152    
## balance      5.737e-03  2.319e-04  24.738  < 2e-16 ***
## studentYes  -6.468e-01  2.363e-01  -2.738  0.00619 ** 
## ---
## 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: 1571.5  on 9996  degrees of freedom
## AIC: 1579.5
## 
## Number of Fisher Scoring iterations: 8

exp(coef(model_logit))

##  (Intercept)       income      balance   studentYes 
## 1.903854e-05 1.000003e+00 1.005753e+00 5.237317e-01