Table of Contents
chi square test eg. 1
- code01
- output01
Loading...
> # install.packages("MASS")
> library(MASS)
>
> print(str(survey))
'data.frame': 237 obs. of 12 variables:
$ Sex : Factor w/ 2 levels "Female","Male": 1 2 2 2 2 1 2 1 2 2 ...
$ Wr.Hnd: num 18.5 19.5 18 18.8 20 18 17.7 17 20 18.5 ...
$ NW.Hnd: num 18 20.5 13.3 18.9 20 17.7 17.7 17.3 19.5 18.5 ...
$ W.Hnd : Factor w/ 2 levels "Left","Right": 2 1 2 2 2 2 2 2 2 2 ...
$ Fold : Factor w/ 3 levels "L on R","Neither",..: 3 3 1 3 2 1 1 3 3 3 ...
$ Pulse : int 92 104 87 NA 35 64 83 74 72 90 ...
$ Clap : Factor w/ 3 levels "Left","Neither",..: 1 1 2 2 3 3 3 3 3 3 ...
$ Exer : Factor w/ 3 levels "Freq","None",..: 3 2 2 2 3 3 1 1 3 3 ...
$ Smoke : Factor w/ 4 levels "Heavy","Never",..: 2 4 3 2 2 2 2 2 2 2 ...
$ Height: num 173 178 NA 160 165 ...
$ M.I : Factor w/ 2 levels "Imperial","Metric": 2 1 NA 2 2 1 1 2 2 2 ...
$ Age : num 18.2 17.6 16.9 20.3 23.7 ...
NULL
> ??MASS::survevy
>
> wh.clap = data.frame(survey$Clap,survey$W.Hnd)
> wh.clap.tbl = table(survey$Clap,survey$W.Hnd)
> wh.clap.tbl
Left Right
Left 9 29
Neither 5 45
Right 4 143
> chisq <- chisq.test(wh.clap.tbl)
경고메시지(들):
chisq.test(wh.clap.tbl)에서:
카이제곱 approximation은 정확하지 않을수도 있습니다
> chisq
Pearson's Chi-squared test
data: wh.clap.tbl
X-squared = 19.252, df = 2, p-value = 6.598e-05
> o <- chisq$observed
> e <- chisq$expected
> o
Left Right
Left 9 29
Neither 5 45
Right 4 143
> round(e, 2)
Left Right
Left 2.91 35.09
Neither 3.83 46.17
Right 11.26 135.74
> res <- (e-o)/sqrt(e)
> round(res,2)
Left Right
Left -3.57 1.03
Neither -0.60 0.17
Right 2.16 -0.62
> chisq.cal <- sum(res^2)
> p.val <- pchisq(chisq.cal, df=2, lower.tail = F)
> chisq.cal
[1] 19.25239
> p.val
[1] 6.597765e-05
> chisq
Pearson's Chi-squared test
data: wh.clap.tbl
X-squared = 19.252, df = 2, p-value = 6.598e-05
>
> barplot(wh.clap.tbl, beside = TRUE,
+ col = c("red", "lightgreen", "blue"),
+ main = "wh vs ex",
+ xlab = "Exercise Level", ylab = "Number of Students")
>
> legend("center", legend = rownames(wh.clap.tbl),
+ fill = c("red", "lightgreen" ,"blue"))
>
>
chi square test eg. 2
- code02
- output02
Loading...
> ####################
> file_path <- "https://www.sthda.com/sthda/RDoc/data/housetasks.txt"
> housetasks <- read.delim(file_path, row.names = 1)
> housetasks
Wife Alternating Husband Jointly
Laundry 156 14 2 4
Main_meal 124 20 5 4
Dinner 77 11 7 13
Breakfeast 82 36 15 7
Tidying 53 11 1 57
Dishes 32 24 4 53
Shopping 33 23 9 55
Official 12 46 23 15
Driving 10 51 75 3
Finances 13 13 21 66
Insurance 8 1 53 77
Repairs 0 3 160 2
Holidays 0 1 6 153
>
> chisq <- chisq.test(housetasks)
> chisq
Pearson's Chi-squared test
data: housetasks
X-squared = 1944.5, df = 36, p-value < 2.2e-16
>
> o <- chisq$observed
> e <- chisq$expected
> o
Wife Alternating Husband Jointly
Laundry 156 14 2 4
Main_meal 124 20 5 4
Dinner 77 11 7 13
Breakfeast 82 36 15 7
Tidying 53 11 1 57
Dishes 32 24 4 53
Shopping 33 23 9 55
Official 12 46 23 15
Driving 10 51 75 3
Finances 13 13 21 66
Insurance 8 1 53 77
Repairs 0 3 160 2
Holidays 0 1 6 153
> round(e,2)
Wife Alternating Husband Jointly
Laundry 60.55 25.63 38.45 51.37
Main_meal 52.64 22.28 33.42 44.65
Dinner 37.16 15.73 23.59 31.52
Breakfeast 48.17 20.39 30.58 40.86
Tidying 41.97 17.77 26.65 35.61
Dishes 38.88 16.46 24.69 32.98
Shopping 41.28 17.48 26.22 35.02
Official 33.03 13.98 20.97 28.02
Driving 47.82 20.24 30.37 40.57
Finances 38.88 16.46 24.69 32.98
Insurance 47.82 20.24 30.37 40.57
Repairs 56.77 24.03 36.05 48.16
Holidays 55.05 23.30 34.95 46.70
> cs.cal <- sum((e-o)^2/e)
> cs.cal
[1] 1944.456
> dim(housetasks)
[1] 13 4
> dim(housetasks)-1
[1] 12 3
> pchisq(cs.cal, 12*3, lower.tail = F)
[1] 0
> chisq
Pearson's Chi-squared test
data: housetasks
X-squared = 1944.5, df = 36, p-value < 2.2e-16
chi square test eg. 3
- code03
- output03
Loading...
>
> #Author DataFlair
> df <- read.csv("https://goo.gl/j6lRXD") #Reading CSV
> head(df)
id treatment improvement
1 1 treated improved
2 2 treated improved
3 3 not-treated improved
4 4 treated improved
5 5 treated not-improved
6 6 treated not-improved
> tail(df)
id treatment improvement
100 100 not-treated improved
101 101 treated improved
102 102 treated improved
103 103 not-treated not-improved
104 104 treated improved
105 105 not-treated not-improved
> str(df)
'data.frame': 105 obs. of 3 variables:
$ id : int 1 2 3 4 5 6 7 8 9 10 ...
$ treatment : chr "treated" "treated" "not-treated" "treated" ...
$ improvement: chr "improved" "improved" "improved" "improved" ...
> df$treatment <- factor(df$treatment)
> df$improvement <- factor(df$improvement)
> str(df)
'data.frame': 105 obs. of 3 variables:
$ id : int 1 2 3 4 5 6 7 8 9 10 ...
$ treatment : Factor w/ 2 levels "not-treated",..: 2 2 1 2 2 2 1 2 1 2 ...
$ improvement: Factor w/ 2 levels "improved","not-improved": 1 1 1 1 2 2 2 2 1 1 ...
> df.tbl<-table(df$treatment, df$improvement)
> df.tbl
improved not-improved
not-treated 26 29
treated 35 15
>
> chisq <- chisq.test(df.tbl, correct=F)
> chisq
Pearson's Chi-squared test
data: df.tbl
X-squared = 5.5569, df = 1, p-value = 0.01841
>
> # or the below works also
> chisq <- chisq.test(df$treatment, df$improvement, correct=F)
> chisq
Pearson's Chi-squared test
data: df$treatment and df$improvement
X-squared = 5.5569, df = 1, p-value = 0.01841
>
> o <- chisq$observed
> e <- chisq$expected
> o
df$improvement
df$treatment improved not-improved
not-treated 26 29
treated 35 15
> round(e,2)
df$improvement
df$treatment improved not-improved
not-treated 31.95 23.05
treated 29.05 20.95
> r <- (e-o)/sqrt(e) # this is called residuals
> round(r, 3)
df$improvement
df$treatment improved not-improved
not-treated 1.053 -1.240
treated -1.104 1.300
> round(chisq$residuals, 3)
df$improvement
df$treatment improved not-improved
not-treated -1.053 1.240
treated 1.104 -1.300
>
> cs.tmp <- sum(chisq$residuals^2)
> cs.tmp
[1] 5.55692
> cs.cal <- sum((e-o)^2/e)
> pchisq(cs.cal, 1,lower.tail = F)
[1] 0.01840777
> cs.cal
[1] 5.55692
> chisq
Pearson's Chi-squared test
data: df$treatment and df$improvement
X-squared = 5.5569, df = 1, p-value = 0.01841
>
> library(corrplot)
> corrplot(chisq$residuals, is.cor = FALSE)
>
> contrib <- 100*chisq$residuals^2/chisq$statistic
> round(contrib, 3)
df$improvement
df$treatment improved not-improved
not-treated 19.955 27.664
treated 21.950 30.431
>
> # Visualize the contribution
> corrplot(contrib, is.cor = FALSE)
residual value $(\text{sqrt}((e-o)^2/e))$ of each cell
contribution of each cell
