library(party)
## Loading required package: survival
## Loading required package: splines
## Loading required package: grid
## Loading required package: modeltools
## Loading required package: stats4
## Loading required package: coin
## Loading required package: mvtnorm
## Loading required package: zoo
## Attaching package: 'zoo'
## The following object(s) are masked from 'package:base':
##
## as.Date, as.Date.numeric
## Loading required package: sandwich
## Loading required package: strucchange
## Loading required package: vcd
## Loading required package: MASS
## Loading required package: colorspace
data(airquality)
summary(airquality)
## Ozone Solar.R Wind Temp
## Min. : 1.0 Min. : 7 Min. : 1.70 Min. :56.0
## 1st Qu.: 18.0 1st Qu.:116 1st Qu.: 7.40 1st Qu.:72.0
## Median : 31.5 Median :205 Median : 9.70 Median :79.0
## Mean : 42.1 Mean :186 Mean : 9.96 Mean :77.9
## 3rd Qu.: 63.2 3rd Qu.:259 3rd Qu.:11.50 3rd Qu.:85.0
## Max. :168.0 Max. :334 Max. :20.70 Max. :97.0
## NA's :37 NA's :7
## Month Day
## Min. :5.00 Min. : 1.0
## 1st Qu.:6.00 1st Qu.: 8.0
## Median :7.00 Median :16.0
## Mean :6.99 Mean :15.8
## 3rd Qu.:8.00 3rd Qu.:23.0
## Max. :9.00 Max. :31.0
##
hist(airquality$Ozone, xlim = c(0, 200), ylim = c(0, 50))
airq <- subset(airquality, !is.na(Ozone))
airct <- ctree(Ozone ~ ., data = airq)
airq$pred.Ozone <- predict(airct, data = airq)
## default: boxplots
plot(airct)
## change colors
plot(airct, tp_args = list(col = "blue", fill = hsv(2/3, 0.5, 1)))
## equivalent to
plot(airct, terminal_panel = node_boxplot(airct, col = "blue", fill = hsv(2/3,
0.5, 1)))
### very simple; the mean is given in each terminal node
plot(airct, type = "simple")
### density estimates
plot(airct, terminal_panel = node_density)
### histograms
plot(airct, terminal_panel = node_hist(airct, ymax = 0.06, xscale = c(0, 250)))
summary(airq[, c("Ozone", "pred.Ozone")])
## Ozone pred.Ozone.Ozone
## Min. : 1.0 Min. :18.48
## 1st Qu.: 18.0 1st Qu.:18.48
## Median : 31.5 Median :31.14
## Mean : 42.1 Mean :42.13
## 3rd Qu.: 63.2 3rd Qu.:81.63
## Max. :168.0 Max. :81.63
plot(airq$Ozone, airq$pred.Ozone, xlim = c(0, 200), ylim = c(0, 200))
lm.result <- lm(Ozone ~ ., data = airq[, c(1:4)])
summary(lm.result)
##
## Call:
## lm(formula = Ozone ~ ., data = airq[, c(1:4)])
##
## Residuals:
## Min 1Q Median 3Q Max
## -40.48 -14.22 -3.55 10.10 95.62
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -64.3421 23.0547 -2.79 0.0062 **
## Solar.R 0.0598 0.0232 2.58 0.0112 *
## Wind -3.3336 0.6544 -5.09 1.5e-06 ***
## Temp 1.6521 0.2535 6.52 2.4e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 21.2 on 107 degrees of freedom
## (5 observations deleted due to missingness)
## Multiple R-squared: 0.606, Adjusted R-squared: 0.595
## F-statistic: 54.8 on 3 and 107 DF, p-value: <2e-16
plot(airq$Ozone, predict(lm.result, newdata = airq[, c(1:4)]), xlim = c(0, 200),
ylim = c(0, 200))
