課稅價值

x8.24 <- read.csv("C:/Users/tony8/Downloads/x8.24.txt", sep="")

1. Fit MLR

2. 模型比較

price=x8.24$Y
tax=x8.24$X1
location=x8.24$X2
lm1=lm(Y ~ factor(X2)*X1,data = x8.24)
summary(lm1)
## 
## Call:
## lm(formula = Y ~ factor(X2) * X1, data = x8.24)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -10.8470  -2.1639   0.0913   1.9348   9.9836 
## 
## Coefficients:
##                 Estimate Std. Error t value Pr(>|t|)    
## (Intercept)    -126.9052    14.7225  -8.620 4.33e-12 ***
## factor(X2)1      76.0215    30.1314   2.523  0.01430 *  
## X1                2.7759     0.1963  14.142  < 2e-16 ***
## factor(X2)1:X1   -1.1075     0.4055  -2.731  0.00828 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 3.893 on 60 degrees of freedom
## Multiple R-squared:  0.8233, Adjusted R-squared:  0.8145 
## F-statistic: 93.21 on 3 and 60 DF,  p-value: < 2.2e-16
lm2=lm(Y ~ factor(X2)+X1,data = x8.24)
summary(lm2)
## 
## Call:
## lm(formula = Y ~ factor(X2) + X1, data = x8.24)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -11.4141  -2.2927  -0.1456   1.8678   9.2341 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept) -107.4597    13.5509   -7.93 5.80e-11 ***
## factor(X2)1   -6.2057     1.1933   -5.20 2.45e-06 ***
## X1             2.5165     0.1806   13.93  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 4.093 on 61 degrees of freedom
## Multiple R-squared:  0.8014, Adjusted R-squared:  0.7949 
## F-statistic: 123.1 on 2 and 61 DF,  p-value: < 2.2e-16
lm3=lm(Y ~ factor(X2):X1,data = x8.24)
summary(lm3)
## 
## Call:
## lm(formula = Y ~ factor(X2):X1, data = x8.24)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -11.2898  -2.3282  -0.1336   1.9151   9.1627 
## 
## Coefficients:
##                 Estimate Std. Error t value Pr(>|t|)    
## (Intercept)    -108.7558    13.3984  -8.117 2.77e-11 ***
## factor(X2)0:X1    2.5341     0.1787  14.183  < 2e-16 ***
## factor(X2)1:X1    2.4491     0.1813  13.512  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 4.06 on 61 degrees of freedom
## Multiple R-squared:  0.8046, Adjusted R-squared:  0.7982 
## F-statistic: 125.6 on 2 and 61 DF,  p-value: < 2.2e-16
lm4=lm(Y ~ X1,data = x8.24)
summary(lm4)
## 
## Call:
## lm(formula = Y ~ X1, data = x8.24)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -16.0655  -2.6918   0.1111   2.6900  11.0356 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept) -118.7938    15.9380  -7.454 3.52e-10 ***
## X1             2.6474     0.2131  12.421  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 4.878 on 62 degrees of freedom
## Multiple R-squared:  0.7133, Adjusted R-squared:  0.7087 
## F-statistic: 154.3 on 1 and 62 DF,  p-value: < 2.2e-16
anova(lm2,lm1)#2公司類別迴歸線截距與斜率都不同
## Analysis of Variance Table
## 
## Model 1: Y ~ factor(X2) + X1
## Model 2: Y ~ factor(X2) * X1
##   Res.Df    RSS Df Sum of Sq      F   Pr(>F)   
## 1     61 1022.1                                
## 2     60  909.1  1       113 7.4578 0.008281 **
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(lm4,lm2)#2公司類別迴歸線截距不同斜率相同
## Analysis of Variance Table
## 
## Model 1: Y ~ X1
## Model 2: Y ~ factor(X2) + X1
##   Res.Df    RSS Df Sum of Sq      F    Pr(>F)    
## 1     62 1475.2                                  
## 2     61 1022.1  1    453.15 27.044 2.447e-06 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(lm3,lm1)#2公司類別迴歸線截距與斜率都不同
## Analysis of Variance Table
## 
## Model 1: Y ~ factor(X2):X1
## Model 2: Y ~ factor(X2) * X1
##   Res.Df    RSS Df Sum of Sq      F Pr(>F)  
## 1     61 1005.5                             
## 2     60  909.1  1    96.449 6.3655 0.0143 *
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(lm4,lm3)#2公司類別迴歸線截距相同斜率不同
## Analysis of Variance Table
## 
## Model 1: Y ~ X1
## Model 2: Y ~ factor(X2):X1
##   Res.Df    RSS Df Sum of Sq      F    Pr(>F)    
## 1     62 1475.2                                  
## 2     61 1005.5  1     469.7 28.493 1.463e-06 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1