Lab 2
Toluca Company Example (Section 1.6)
> data<-read.table("/afs/stat.lsa.umich.edu/users/student/kutsyy/.public_html/classes/stat413.data/CH01TA01.DAT")
> data
    V1  V2
 1  80 399
 2  30 121
 3  50 221
 4  90 376
 5  70 361
 6  60 224
 7 120 546
 8  80 352
 9 100 353
10  50 157
11  40 160
12  70 252
13  90 389
14  20 113
15 110 435
16 100 420
17  30 212
18  50 268
19  90 377
20 110 421
21  30 273
22  90 468
23  40 244
24  80 342
25  70 323
> fit<-lm(V1~V2,data=data)
> summary(fit)
Call: lm(formula = V1 ~ V2, data = data)
Residuals:
    Min     1Q Median    3Q   Max
 -30.96 -9.811  2.346 5.337 20.63
Coefficients:
               Value Std. Error  t value Pr(>|t|)
(Intercept)  -1.8583   7.4105    -0.2508   0.8042
         V2   0.2301   0.0224    10.2896   0.0000
Residual standard error: 12.4 on 23 degrees of freedom
Multiple R-Squared: 0.8215
F-statistic: 105.9 on 1 and 23 degrees of freedom, the p-value is 4.449e-10
Correlation of Coefficients:
   (Intercept)
V2 -0.9424
>  plot(data$V2,data$V1,xlab="LOT SIZE",ylab="HOURS",main="See Figure 1.10(b) in the book")
> abline(fit$coef)
> fit$coef
 (Intercept)        V2
   -1.858251 0.2301084

Problem 1.20
a)

>data<-read.table("/afs/stat.lsa.umich.edu/users/student/kutsyy/.public_html/classes/stat413.data/CH01PR20.DAT")
>data
    V1 V2
 1  97  7
 2  86  6
 3  78  5
 4  10  1
 5  75  5
 6  62  4
 7 101  7
 8  39  3
 9  53  4
10  33  2
11 118  8
12  65  5
13  25  2
14  71  5
15 105  7
16  17  1
17  49  4
18  68  5
> motif()
> fit<-lm(V1~V2, data=data)
> summary(fit)
Call: lm(formula = V1 ~ V2, data = data)
Residuals:
    Min    1Q  Median    3Q   Max
 -7.631 -3.25 -0.2383 4.023 6.631
Coefficients:
               Value Std. Error  t value Pr(>|t|)
(Intercept)  -2.3221   2.5644    -0.9055   0.3786
         V2  14.7383   0.5193    28.3834   0.0000
Residual standard error: 4.482 on 16 degrees of freedom
Multiple R-Squared: 0.9805
F-statistic: 805.6 on 1 and 16 degrees of freedom, the p-value is 4.108e-15
Correlation of Coefficients:
   (Intercept)
V2 -0.9112
b)
> plot(data$V2,data$V1)
> abline(fit$coef)
c)
b0 is intercept
d)
> x0<-c(1,5)
> x0%*%fit$coef
         [,1]
[1,] 71.36913
> fit$coef[1]+fit$coef[2]*5
 (Intercept)
    71.36913