#
# An R script for IQ_Beh data set
#
#
dta <- read.table("IQ_Beh.txt", header = T, row.names = 1)
#
str(dta)
## 'data.frame': 94 obs. of 3 variables:
## $ Dep: Factor w/ 2 levels "D","N": 2 2 2 2 1 2 2 2 2 2 ...
## $ IQ : int 103 124 124 104 96 92 124 99 92 116 ...
## $ BP : int 4 12 9 3 3 3 6 4 3 9 ...
#
head(dta)
## Dep IQ BP
## 1 N 103 4
## 2 N 124 12
## 3 N 124 9
## 4 N 104 3
## 5 D 96 3
## 6 N 92 3
#
class(dta)
## [1] "data.frame"
#
dim(dta)
## [1] 94 3
#
names(dta)
## [1] "Dep" "IQ" "BP"
#
is.vector(dta$BP)
## [1] TRUE
#
dta[1, ]
## Dep IQ BP
## 1 N 103 4
#
dta[1:3, "IQ"]
## [1] 103 124 124
#
tail(dta[order(dta$BP), ])
## Dep IQ BP
## 16 N 89 11
## 58 N 117 11
## 66 N 126 11
## 2 N 124 12
## 73 D 99 13
## 12 D 22 17
#
tail(dta[order(-dta$BP), ], 4)
## Dep IQ BP
## 77 N 124 1
## 80 N 121 1
## 24 N 106 0
## 75 N 122 0
#
with(dta, hist(IQ, xlab = "IQ", main = ""))
#
boxplot(BP ~ Dep, data = dta,
xlab = "Depression",
ylab = "Behavior problem score")
#
plot(IQ ~ BP, data = dta, pch = 20, col = dta$Dep,
xlab = "Behavior problem score", ylab = "IQ")
grid()
#
plot(BP ~ IQ, data = dta, type = "n",
ylab = "Behavior problem score", xlab = "IQ")
text(dta$IQ, dta$BP, labels = dta$Dep, cex = 0.5)
abline(lm(BP ~ IQ, data = dta, subset = Dep == "D"))
abline(lm(BP ~ IQ, data = dta, subset = Dep == "N"), lty = 2)
## end
t.test(IQ~Dep, data=dta)
##
## Welch Two Sample t-test
##
## data: IQ by Dep
## t = -1.6374, df = 15.53, p-value = 0.1216
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -26.926586 3.490299
## sample estimates:
## mean in group D mean in group N
## 101.0667 112.7848
##p值>.05未達顯著差異(沮喪和IQ之間沒有差異)
t.test(BP~Dep, data=dta)
##
## Welch Two Sample t-test
##
## data: BP by Dep
## t = 1.4924, df = 17.14, p-value = 0.1538
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.6637017 3.8788916
## sample estimates:
## mean in group D mean in group N
## 7.000000 5.392405
##p值>.05未達顯著差異(沮喪和行為之間沒有差異)
cor.test(dta$IQ, dta$BP)
##
## Pearson's product-moment correlation
##
## data: dta$IQ and dta$BP
## t = -3.8088, df = 92, p-value = 0.0002518
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.5319037 -0.1798969
## sample estimates:
## cor
## -0.3690615
##p值<.05達顯著差異(IQ和行為具有相關)
dta <- read.table("C:/tmp/usBirths2015.txt",header=T,stringsAsFactor=FALSE)
str(dta)
## 'data.frame': 12 obs. of 2 variables:
## $ birth: int 325955 298058 328923 320832 327917 330541 353415 351791 347516 339007 ...
## $ month: chr "January" "February" "March" "April" ...
dta$month <- c("spring", "spring", "spring", "summer", "summer", "summer", "autumn", "autumn", "autumn", "winter", "winter", "winter")
dta
## birth month
## 1 325955 spring
## 2 298058 spring
## 3 328923 spring
## 4 320832 summer
## 5 327917 summer
## 6 330541 summer
## 7 353415 autumn
## 8 351791 autumn
## 9 347516 autumn
## 10 339007 winter
## 11 318820 winter
## 12 335722 winter
aggregate(birth ~ month, mean, data=dta)
## month birth
## 1 autumn 350907.3
## 2 spring 317645.3
## 3 summer 326430.0
## 4 winter 331183.0
dta <- read.table("C:/tmp/readingtimes.txt",header=T,stringsAsFactor=FALSE)
dta
## Snt Sp Wrds New S01 S02 S03 S04 S05 S06 S07 S08 S09 S10
## 1 1 1 13 1 3.429 2.795 4.161 3.071 3.625 3.161 3.232 7.161 1.536 4.063
## 2 2 2 16 3 6.482 5.411 4.491 5.063 9.295 5.643 8.357 4.313 2.946 6.652
## 3 3 3 9 2 1.714 2.339 3.018 2.464 6.045 2.455 4.920 3.366 1.375 2.179
## 4 4 4 9 2 3.679 3.714 2.866 2.732 4.205 6.241 3.723 6.330 1.152 3.661
## 5 5 5 10 3 4.000 2.902 2.991 2.670 3.884 3.223 3.143 6.143 2.759 3.330
## 6 6 6 18 4 6.973 8.018 6.625 7.571 8.795 13.188 11.170 6.071 7.964 7.866
## 7 7 7 6 1 2.634 1.750 2.268 2.884 3.491 3.688 2.054 1.696 1.455 3.705
dta01 <- mean(dta$S01)
dta01
## [1] 4.130143
dta02 <- mean(dta$S02)
dta02
## [1] 3.847
dta03 <- mean(dta$S03)
dta03
## [1] 3.774286
dta04 <- mean(dta$S04)
dta04
## [1] 3.779286
dta05 <- mean(dta$S05)
dta05
## [1] 5.62
dta06 <- mean(dta$S06)
dta06
## [1] 5.371286
dta07 <- mean(dta$S07)
dta07
## [1] 5.228429
dta08 <- mean(dta$S08)
dta08
## [1] 5.011429
dta09 <- mean(dta$S09)
dta09
## [1] 2.741
dta10 <- mean(dta$S10)
dta10
## [1] 4.493714
dtr <- apply(dta[,5:14], 2, mean)
dtr
## S01 S02 S03 S04 S05 S06 S07 S08
## 4.130143 3.847000 3.774286 3.779286 5.620000 5.371286 5.228429 5.011429
## S09 S10
## 2.741000 4.493714
order(dtr)
## [1] 9 3 4 2 1 10 8 7 6 5