Heating

mydata <- read.csv2("Energy.csv")
head(mydata)

##   Size Consumption HeatingType
## 1  130    2954.896         Gas
## 2   80    2198.613         Gas
## 3  100    2682.367         Gas
## 4   40    1808.698         Gas
## 5  155    3037.554         Gas
## 6   80    2550.555         Gas

Description of variables:

• Size (size) of an apartment in m2.
• Consumption: consumption of energy in kWh.
• HeatingType: type of heating (Gas or Electricity)

mydata$HeatingType <- factor(mydata$HeatingType, 
                             levels = c("Gas", "Electricity"), 
                             labels = c("Gas", "Electricity"))

library(car)

## Loading required package: carData

scatterplot(Consumption ~ Size | HeatingType, 
            ylab = "Consumption of energy in kWh", 
            xlab = "Size of an apartment in m2", 
            smooth = FALSE,
            boxplots = FALSE,
            data = mydata)

fit <- lm(Consumption ~ Size + HeatingType + Size:HeatingType,
           data = mydata)

summary(fit)

## 
## Call:
## lm(formula = Consumption ~ Size + HeatingType + Size:HeatingType, 
##     data = mydata)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -708.05  -96.61   -4.28   88.68  649.28 
## 
## Coefficients:
##                             Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                 1264.295    148.923   8.490 4.07e-10 ***
## Size                          12.562      1.415   8.878 1.35e-10 ***
## HeatingTypeElectricity       964.379    209.522   4.603 5.02e-05 ***
## Size:HeatingTypeElectricity   12.265      2.178   5.632 2.16e-06 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 235.5 on 36 degrees of freedom
## Multiple R-squared:  0.9608, Adjusted R-squared:  0.9576 
## F-statistic: 294.3 on 3 and 36 DF,  p-value: < 2.2e-16