EX1
require(nlme)
## Loading required package: nlme
## Warning: package 'nlme' was built under R version 3.4.4
require(lattice)
## Loading required package: lattice
## Warning: package 'lattice' was built under R version 3.4.4
dta1 <- Oxboys
str(dta1)
## Classes 'nfnGroupedData', 'nfGroupedData', 'groupedData' and 'data.frame': 234 obs. of 4 variables:
## $ Subject : Ord.factor w/ 26 levels "10"<"26"<"25"<..: 13 13 13 13 13 13 13 13 13 5 ...
## $ age : num -1 -0.7479 -0.463 -0.1643 -0.0027 ...
## $ height : num 140 143 145 147 148 ...
## $ Occasion: Ord.factor w/ 9 levels "1"<"2"<"3"<"4"<..: 1 2 3 4 5 6 7 8 9 1 ...
## - attr(*, "formula")=Class 'formula' language height ~ age | Subject
## .. ..- attr(*, ".Environment")=<environment: R_GlobalEnv>
## - attr(*, "labels")=List of 2
## ..$ y: chr "Height"
## ..$ x: chr "Centered age"
## - attr(*, "units")=List of 1
## ..$ y: chr "(cm)"
## - attr(*, "FUN")=function (x)
## ..- attr(*, "source")= chr "function (x) max(x, na.rm = TRUE)"
## - attr(*, "order.groups")= logi TRUE
head(dta1)
## Grouped Data: height ~ age | Subject
## Subject age height Occasion
## 1 1 -1.0000 140.5 1
## 2 1 -0.7479 143.4 2
## 3 1 -0.4630 144.8 3
## 4 1 -0.1643 147.1 4
## 5 1 -0.0027 147.7 5
## 6 1 0.2466 150.2 6
xyplot(height ~ age | Subject, data =dta1 , type = c("r", "g", "p"),
index.cond = function(x, y) coef(lm(y ~ x))[1])
EX2
require(ggplot2)
## Loading required package: ggplot2
dta2<-read.csv("income_tw.csv", h=T)
str(dta2)
## 'data.frame': 41 obs. of 2 variables:
## $ Income: Factor w/ 41 levels "1,000,000 to 1,069,999",..: 7 8 9 11 12 13 14 15 16 17 ...
## $ Count : int 807160 301650 313992 329290 369583 452671 495387 517779 557786 584497 ...
head(dta2)
## Income Count
## 1 160,000 and under 807160
## 2 160,000 to 179,999 301650
## 3 180,000 to 199,999 313992
## 4 200,000 to 219,999 329290
## 5 220,000 to 239,999 369583
## 6 240,000 to 259,999 452671
dta2$Income<-factor(dta2$Income,levels =dta2$Income[order(dta2$Count)] )
ggplot(dta2, aes(Count/10000, Income)) +
geom_point() +
geom_segment(aes(x = 0, xend = Count/10000, yend=Income)) +
labs(x= "Number of persons(x10,000)", y = "Income", title = "Distribution of personal disposable income in Taiwan in 2015")
EX3
require(tidyr)
## Loading required package: tidyr
dta3<-read.csv("brainsize.txt", h=T, sep = " ")
str(dta3)
## 'data.frame': 40 obs. of 8 variables:
## $ Sbj : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Gender : Factor w/ 2 levels "Female","Male": 1 2 2 2 1 1 1 1 2 2 ...
## $ FSIQ : int 133 140 139 133 137 99 138 92 89 133 ...
## $ VIQ : int 132 150 123 129 132 90 136 90 93 114 ...
## $ PIQ : int 124 124 150 128 134 110 131 98 84 147 ...
## $ Weight : int 118 NA 143 172 147 146 138 175 134 172 ...
## $ Height : num 64.5 72.5 73.3 68.8 65 69 64.5 66 66.3 68.8 ...
## $ MRICount: int 816932 1001121 1038437 965353 951545 928799 991305 854258 904858 955466 ...
head(dta3)
## Sbj Gender FSIQ VIQ PIQ Weight Height MRICount
## 1 1 Female 133 132 124 118 64.5 816932
## 2 2 Male 140 150 124 NA 72.5 1001121
## 3 3 Male 139 123 150 143 73.3 1038437
## 4 4 Male 133 129 128 172 68.8 965353
## 5 5 Female 137 132 134 147 65.0 951545
## 6 6 Female 99 90 110 146 69.0 928799
EX3-1:Are there gender differences in the three IQ scores?
dta3 %>% gather(Type, IQ, 3:5) %>%
ggplot(aes(Type, IQ, color = Gender))+
stat_summary(fun.data = mean_se, geom = "pointrange", position = position_dodge(.2))+
theme(legend.position = "top")
VIQ和FSIQ可能有性別差異，PIQ可能沒有。
EX3-2:Is the relationship between height and weight gender dependent?
ggplot(dta3, aes(Weight, Height, color = Gender)) +
geom_point(na.rm = T) +
stat_smooth(aes(color = Gender), method = "lm", se = F,na.rm = T) +
theme_bw()
男女身高與體重之斜率相近
EX3-3:Is the relationship between height and weight gender dependent?
read.table("brainsize.txt", header = T) %>%
gather(IQtype, IQvalue, 3:5) %>%
ggplot(aes(IQvalue, MRICount, color = Gender)) +
geom_point() +
stat_smooth(method = "lm", se = F) +
facet_grid(. ~ IQtype) +
labs(y = "Brain Size")
IQ分數和腦容量有性別差異