week7
2026-11-15
library(ggplot2)
data("ChickWeight")
ggplot(ChickWeight, aes(x = weight)) +
geom_histogram(binwidth = 50, fill = "blue", color = "black") +
labs(title = "Distribution of Chick Weights", x = "Weight", y = "Frequency")
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
library(tidyr)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union#long to wide
wide_data <- ChickWeight %>%
spread(key = Time, value = weight)
head(wide_data)## Chick Diet 0 2 4 6 8 10 12 14 16 18 20 21
## 1 18 1 39 35 NA NA NA NA NA NA NA NA NA NA
## 2 16 1 41 45 49 51 57 51 54 NA NA NA NA NA
## 3 15 1 41 49 56 64 68 68 67 68 NA NA NA NA
## 4 13 1 41 48 53 60 65 67 71 70 71 81 91 96
## 5 9 1 42 51 59 68 85 96 90 92 93 100 100 98
## 6 20 1 41 47 54 58 65 73 77 89 98 107 115 117tail(wide_data)## Chick Diet 0 2 4 6 8 10 12 14 16 18 20 21
## 45 47 4 41 53 66 79 100 123 148 157 168 185 210 205
## 46 49 4 40 53 64 85 108 128 152 166 184 203 233 237
## 47 46 4 40 52 62 82 101 120 144 156 173 210 231 238
## 48 50 4 41 54 67 84 105 122 155 175 205 234 264 264
## 49 42 4 42 49 63 84 103 126 160 174 204 234 269 281
## 50 48 4 39 50 62 80 104 125 154 170 222 261 303 322Including Plots
You can also embed plots, for example:
#wide to long
long_data <- wide_data %>%
gather(key = "Time", value = "weight",-Chick,-Diet)
head(wide_data)## Chick Diet 0 2 4 6 8 10 12 14 16 18 20 21
## 1 18 1 39 35 NA NA NA NA NA NA NA NA NA NA
## 2 16 1 41 45 49 51 57 51 54 NA NA NA NA NA
## 3 15 1 41 49 56 64 68 68 67 68 NA NA NA NA
## 4 13 1 41 48 53 60 65 67 71 70 71 81 91 96
## 5 9 1 42 51 59 68 85 96 90 92 93 100 100 98
## 6 20 1 41 47 54 58 65 73 77 89 98 107 115 117tail(wide_data)## Chick Diet 0 2 4 6 8 10 12 14 16 18 20 21
## 45 47 4 41 53 66 79 100 123 148 157 168 185 210 205
## 46 49 4 40 53 64 85 108 128 152 166 184 203 233 237
## 47 46 4 40 52 62 82 101 120 144 156 173 210 231 238
## 48 50 4 41 54 67 84 105 122 155 175 205 234 264 264
## 49 42 4 42 49 63 84 103 126 160 174 204 234 269 281
## 50 48 4 39 50 62 80 104 125 154 170 222 261 303 322Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.
shapiro_test_result <- shapiro.test(ChickWeight$weight)
shapiro_test_result##
## Shapiro-Wilk normality test
##
## data: ChickWeight$weight
## W = 0.90866, p-value < 2.2e-16format(shapiro_test_result$p.value, scientific = FALSE)## [1] "0.000000000000000003873675"#사료 1이랑 사료2랑의 weight 비교
diet_1_weight <- ChickWeight %>%
filter(Diet == 1) %>%
select(weight)
#사료 1이랑 사료2랑의 weight 비교
diet_2_weight <- ChickWeight %>%
filter(Diet == 2) %>%
select(weight)
wilcox_test_result <- wilcox.test(diet_1_weight$weight, diet_2_weight$weight)
wilcox_test_result##
## Wilcoxon rank sum test with continuity correction
##
## data: diet_1_weight$weight and diet_2_weight$weight
## W = 11213, p-value = 0.02181
## alternative hypothesis: true location shift is not equal to 0library(MASS)##
## Attaching package: 'MASS'## The following object is masked from 'package:dplyr':
##
## selectdata("Cars93")
summary(Cars93)## Manufacturer Model Type Min.Price Price
## Chevrolet: 8 100 : 1 Compact:16 Min. : 6.70 Min. : 7.40
## Ford : 8 190E : 1 Large :11 1st Qu.:10.80 1st Qu.:12.20
## Dodge : 6 240 : 1 Midsize:22 Median :14.70 Median :17.70
## Mazda : 5 300E : 1 Small :21 Mean :17.13 Mean :19.51
## Pontiac : 5 323 : 1 Sporty :14 3rd Qu.:20.30 3rd Qu.:23.30
## Buick : 4 535i : 1 Van : 9 Max. :45.40 Max. :61.90
## (Other) :57 (Other):87
## Max.Price MPG.city MPG.highway AirBags
## Min. : 7.9 Min. :15.00 Min. :20.00 Driver & Passenger:16
## 1st Qu.:14.7 1st Qu.:18.00 1st Qu.:26.00 Driver only :43
## Median :19.6 Median :21.00 Median :28.00 None :34
## Mean :21.9 Mean :22.37 Mean :29.09
## 3rd Qu.:25.3 3rd Qu.:25.00 3rd Qu.:31.00
## Max. :80.0 Max. :46.00 Max. :50.00
##
## DriveTrain Cylinders EngineSize Horsepower RPM
## 4WD :10 3 : 3 Min. :1.000 Min. : 55.0 Min. :3800
## Front:67 4 :49 1st Qu.:1.800 1st Qu.:103.0 1st Qu.:4800
## Rear :16 5 : 2 Median :2.400 Median :140.0 Median :5200
## 6 :31 Mean :2.668 Mean :143.8 Mean :5281
## 8 : 7 3rd Qu.:3.300 3rd Qu.:170.0 3rd Qu.:5750
## rotary: 1 Max. :5.700 Max. :300.0 Max. :6500
##
## Rev.per.mile Man.trans.avail Fuel.tank.capacity Passengers
## Min. :1320 No :32 Min. : 9.20 Min. :2.000
## 1st Qu.:1985 Yes:61 1st Qu.:14.50 1st Qu.:4.000
## Median :2340 Median :16.40 Median :5.000
## Mean :2332 Mean :16.66 Mean :5.086
## 3rd Qu.:2565 3rd Qu.:18.80 3rd Qu.:6.000
## Max. :3755 Max. :27.00 Max. :8.000
##
## Length Wheelbase Width Turn.circle
## Min. :141.0 Min. : 90.0 Min. :60.00 Min. :32.00
## 1st Qu.:174.0 1st Qu.: 98.0 1st Qu.:67.00 1st Qu.:37.00
## Median :183.0 Median :103.0 Median :69.00 Median :39.00
## Mean :183.2 Mean :103.9 Mean :69.38 Mean :38.96
## 3rd Qu.:192.0 3rd Qu.:110.0 3rd Qu.:72.00 3rd Qu.:41.00
## Max. :219.0 Max. :119.0 Max. :78.00 Max. :45.00
##
## Rear.seat.room Luggage.room Weight Origin Make
## Min. :19.00 Min. : 6.00 Min. :1695 USA :48 Acura Integra: 1
## 1st Qu.:26.00 1st Qu.:12.00 1st Qu.:2620 non-USA:45 Acura Legend : 1
## Median :27.50 Median :14.00 Median :3040 Audi 100 : 1
## Mean :27.83 Mean :13.89 Mean :3073 Audi 90 : 1
## 3rd Qu.:30.00 3rd Qu.:15.00 3rd Qu.:3525 BMW 535i : 1
## Max. :36.00 Max. :22.00 Max. :4105 Buick Century: 1
## NAs :2 NAs :11 (Other) :87#log transformation
Cars93$LogPrice <- log(Cars93$Price)
summary(Cars93$LogPrice)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.001 2.501 2.874 2.865 3.148 4.126hist(Cars93$LogPrice, breaks = 20, main = "Log-Transformed Price")
hist(Cars93$Price, breaks = 20, main = "Original Transformed Price")
#Q-Q plot
qqnorm(Cars93$LogPrice)
qqline(Cars93$LogPrice, col = "red")
#이상치 추가방법
Cars93$Pricewithoutliers <- Cars93$Price
Cars93$Pricewithoutliers[c(1,2,3)] <- c(100,120,150)
qqnorm(Cars93$Pricewithoutliers)
qqline(Cars93$Pricewithoutliers, col = "blue")
#미국산 vs 비미국산
usa_cars <- Cars93$Pricewithoutliers[Cars93$Origin == "USA"]
non_usa_cars <- Cars93$Pricewithoutliers[Cars93$Origin != "USA"]
wilcox_test_result <- wilcox.test(usa_cars, non_usa_cars, exact = FALSE)
wilcox_test_result##
## Wilcoxon rank sum test with continuity correction
##
## data: usa_cars and non_usa_cars
## W = 987.5, p-value = 0.4794
## alternative hypothesis: true location shift is not equal to 0#there are no significant difference between usa cars and non usa cars because the p-value is higher than 0.05.library(MASS)
library(ggplot2)
library(dplyr)
data("anorexia")
names(anorexia)## [1] "Treat" "Prewt" "Postwt"summary(anorexia)## Treat Prewt Postwt
## CBT :29 Min. :70.00 Min. : 71.30
## Cont:26 1st Qu.:79.60 1st Qu.: 79.33
## FT :17 Median :82.30 Median : 84.05
## Mean :82.41 Mean : 85.17
## 3rd Qu.:86.00 3rd Qu.: 91.55
## Max. :94.90 Max. :103.60ft_data <- anorexia %>%
filter(Treat == "FT")
#sekecting Prewt from the FT
Prewt_ft <- anorexia %>%
filter(Treat == "FT") %>%
dplyr::select(Prewt)
#sekecting postwt from the FT
Postwt_ft <- anorexia %>%
filter(Treat == "FT") %>%
dplyr::select(Postwt)
#extract the data
Prewt_ft <-ft_data$Prewt
Postwt_ft <-ft_data$Postwthist(Prewt_ft, main = "Weight Before Treatment (FT)", xlab = "Pre-treatment Weight", col = "lightblue")
hist(Postwt_ft , main = "Weight After Treatment (FT)", xlab = "Post-treatment Weight", col = "lightgreen")
shapiro_pre1 <- shapiro.test(Prewt_ft)
shapiro_pre1##
## Shapiro-Wilk normality test
##
## data: Prewt_ft
## W = 0.98821, p-value = 0.9972shapiro_pre1 <- shapiro.test(Postwt_ft)
shapiro_pre1##
## Shapiro-Wilk normality test
##
## data: Postwt_ft
## W = 0.83928, p-value = 0.007391#before weight is normal
#after weight is not normal
#so we use the wilconxon signed-rank test
wilcox_test_result <- wilcox.test(Prewt_ft, Postwt_ft, paired = TRUE, exact = FALSE)
print(wilcox_test_result)##
## Wilcoxon signed rank test with continuity correction
##
## data: Prewt_ft and Postwt_ft
## V = 11, p-value = 0.002091
## alternative hypothesis: true location shift is not equal to 0#There are significant differences between preweight and postweight as the p-value is 0.002091.