［R］例3.3 配達時間 (3)（「線形回帰分析」、pp.113-114）

簡略化のため、lm関数を使用して計算している。

> dtf <- read.csv("table3_1.csv", header = TRUE)
> xx2i <- dtf$CASE
> xx3i <- dtf$DIS ^ 2 / 1.e5
> yyi <- dtf$DVT
> # (3.64)式
> r <- lm(yyi[-c(11)] ~ xx2i[-c(11)] + xx3i[-c(11)])
> print(summary(r))
Call:
lm(formula = yyi[-c(11)] ~ xx2i[-c(11)] + xx3i[-c(11)])
Residuals:
    Min      1Q  Median      3Q     Max 
-3.8002 -1.2991  0.3215  1.3196  3.0112 
Coefficients:
             Estimate Std. Error t value Pr(>|t|)    
(Intercept)    6.4226     0.7920   8.110 6.62e-08 ***
xx2i[-c(11)]   1.3376     0.1196  11.182 2.65e-10 ***
xx3i[-c(11)]   1.4969     0.1831   8.178 5.78e-08 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 2.125 on 21 degrees of freedom
Multiple R-squared:  0.9826,    Adjusted R-squared:  0.9809 
F-statistic: 592.7 on 2 and 21 DF,  p-value: < 2.2e-16
> # (3.66)式
> ddi <- rep(0., nrow(dtf))
> ddi[11] <- 1
> r <- lm(yyi ~ xx2i + xx3i + ddi)
> print(summary(r))
Call:
lm(formula = yyi ~ xx2i + xx3i + ddi)
Residuals:
   Min     1Q Median     3Q    Max 
-3.800 -1.279  0.303  1.298  3.011 
Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)   6.4226     0.7920   8.110 6.62e-08 ***
xx2i          1.3376     0.1196  11.182 2.65e-10 ***
xx3i          1.4969     0.1831   8.178 5.78e-08 ***
ddi           5.4200     2.2536   2.405   0.0255 *  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 2.125 on 21 degrees of freedom
Multiple R-squared:  0.9836,    Adjusted R-squared:  0.9813 
F-statistic: 419.9 on 3 and 21 DF,  p-value: < 2.2e-16