mileage <- read.table("C:/Rexamples/fegsub_data.txt", header=T)
View(mileage)
summary(mileage)
mileage1 <- subset(mileage, size <= 2.5, select = c(city, size))
View(mileage1)
summary(mileage1)
attach(mileage1)
displ <- 10*size
regression1 <- lm(city ~ displ)
summary(regression1)
anova(regression1)
attach(regression1)
output1 <- cbind(displ,city,fitted.values,residuals)
View(output1)
summary(output1)
matplot(displ, cbind(city,fitted.values), pch="*", type="pl")
matplot(displ, cbind(residuals,0), pch="*", type="pl")

--------------------- NOTE ------------------------

The first line above which reads the data from the file
"fegsub_data.txt" assumes that this file is in the directory
"C:/Rexamples".  Obey this convention or modify the command.

-------------------------- results ----------------------------------

The remainder of this file is copied and pasted from the RStudio
command window.

--------------------------------------------------------
------------------ EXTRAS ---------------------------
---here are some extra commands which may be of interest ---------

regr1_clim <- predict(regression1, se.fit=TRUE, interval="confidence")
regr1_plim <- predict(regression1, se.fit=TRUE, interval="prediction")
regr1_estimates <- cbind(regr1_clim$fit, regr1_plim$fit[,2:3])
colnames(regr1_estimates) <- c("fit","lclm","uclm","lclp","uclp")
# fitted values conf limits for the mean and for a prediction
# lclm,uclm confidence interval for mean response
# lclp,uclp prediction interval for one observation
regr1_estimates
matplot(displ, cbind(city,fitted.values), pch="*", type="pl")
matplot(displ, cbind(residuals,0), pch="*", type="pl")
matplot(displ, regr1_estimates, lty = c(1,2,2,3,3), type = "l")

plot(regression1)

--------------- END EXTRAS ---------------------------


--------------- output --------------------------

> mileage <- read.table("C:/Rexamples/fegsub_data.txt", header=T)
> View(mileage)
> summary(mileage)
      city          highway          trans
 Min.   :10.00   Min.   :16.00   Min.   :1.000
 1st Qu.:19.00   1st Qu.:26.00   1st Qu.:1.000
 Median :22.50   Median :30.00   Median :1.000
 Mean   :22.39   Mean   :29.77   Mean   :1.232
 3rd Qu.:25.00   3rd Qu.:33.25   3rd Qu.:1.000
 Max.   :39.00   Max.   :46.00   Max.   :2.000
      size           cyl
 Min.   :1.00   Min.   : 3.000
 1st Qu.:1.80   1st Qu.: 4.000
 Median :2.30   Median : 4.000
 Mean   :2.93   Mean   : 5.339
 3rd Qu.:3.80   3rd Qu.: 6.000
 Max.   :6.80   Max.   :12.000
> mileage1 <- subset(mileage, size <= 2.5, select = c(city, size))
> View(mileage1)
> summary(mileage1)
      city            size
 Min.   :19.00   Min.   :1.000
 1st Qu.:23.00   1st Qu.:1.800
 Median :24.00   Median :2.000
 Mean   :25.77   Mean   :1.946
 3rd Qu.:28.00   3rd Qu.:2.200
 Max.   :39.00   Max.   :2.500
> attach(mileage1)
> displ <- 10*size
> regression1 <- lm(city ~ displ)
> summary(regression1)

Call:
lm(formula = city ~ displ)

Residuals:
    Min      1Q  Median      3Q     Max
-4.5229 -1.4119  0.2851  1.7701  2.6891

Coefficients:
            Estimate Std. Error t value Pr(>|t|)
(Intercept)  49.1590     1.8722   26.26  < 2e-16 ***
displ        -1.2020     0.0946  -12.71 2.93e-14 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 2.026 on 33 degrees of freedom
Multiple R-squared:  0.8303,	Adjusted R-squared:  0.8252
F-statistic: 161.5 on 1 and 33 DF,  p-value: 2.933e-14

> anova(regression1)
Analysis of Variance Table

Response: city
          Df Sum Sq Mean Sq F value    Pr(>F)
displ      1 662.72  662.72  161.45 2.933e-14 ***
Residuals 33 135.45    4.10
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
> attach(regression1)
> output1 <- cbind(displ,city,fitted.values,residuals)
> View(output1)
> summary(output1)
     displ            city       fitted.values
 Min.   :10.00   Min.   :19.00   Min.   :19.11
 1st Qu.:18.00   1st Qu.:23.00   1st Qu.:22.71
 Median :20.00   Median :24.00   Median :25.12
 Mean   :19.46   Mean   :25.77   Mean   :25.77
 3rd Qu.:22.00   3rd Qu.:28.00   3rd Qu.:27.52
 Max.   :25.00   Max.   :39.00   Max.   :37.14
   residuals
 Min.   :-4.5229
 1st Qu.:-1.4119
 Median : 0.2851
 Mean   : 0.0000
 3rd Qu.: 1.7701
 Max.   : 2.6891

> matplot(displ, cbind(city,fitted.values), pch="*", type="pl")
> matplot(displ, cbind(residuals,0), pch="*", type="pl")
>