res <- prop.test(x = 95, n = 160, p = 0.5,
correct = FALSE)
# Printing the results
res
##
## 1-sample proportions test without continuity correction
##
## data: 95 out of 160, null probability 0.5
## X-squared = 5.625, df = 1, p-value = 0.01771
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.5163169 0.6667870
## sample estimates:
## p
## 0.59375
# The p-value of the test is 0.01771, which is less than the significance level alpha = 0.05. We can conclude that the proportion of male with cancer is significantly different from 0.5 with a p-value = 0.01771.
# printing the p-value
res$p.value
## [1] 0.01770607
# printing the mean
res$estimate
## p
## 0.59375
# printing the confidence interval
res$conf.int
## [1] 0.5163169 0.6667870
## attr(,"conf.level")
## [1] 0.95
res1 <- prop.test(x = c(490, 400), n = c(500, 500))
# Printing the results
res
##
## 1-sample proportions test without continuity correction
##
## data: 95 out of 160, null probability 0.5
## X-squared = 5.625, df = 1, p-value = 0.01771
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.5163169 0.6667870
## sample estimates:
## p
## 0.59375
# The p-value of the test is 2.36310^{-19}, which is less than the significance level alpha = 0.05. We can conclude that the proportion of smokers is significantly different in the two groups with a p-value = 2.36310^{-19}.
# printing the p-value
res1$p.value
## [1] 2.363439e-19
# printing the mean
res1$estimate
## prop 1 prop 2
## 0.98 0.80
# printing the confidence interval
res1$conf.int
## [1] 0.1408536 0.2191464
## attr(,"conf.level")
## [1] 0.95
tulip <- c(81, 50, 27)
res2 <- chisq.test(tulip, p = c(1/3, 1/3, 1/3))
res2
##
## Chi-squared test for given probabilities
##
## data: tulip
## X-squared = 27.886, df = 2, p-value = 8.803e-07
# The p-value of the test is 8.80310^{-7}, which is less than the significance level alpha = 0.05. We can conclude that the colors are significantly not commonly distributed with a p-value = 8.80310^{-7}.
# Access to the expected values
res2$expected
## [1] 52.66667 52.66667 52.66667
###3/6 (= 1/2) for red ###2/6 ( = 1/3) for yellow ###1/6 for white
tulip <- c(81, 50, 27)
res3 <- chisq.test(tulip, p = c(1/2, 1/3, 1/6))
res3
##
## Chi-squared test for given probabilities
##
## data: tulip
## X-squared = 0.20253, df = 2, p-value = 0.9037
# The p-value of the test is 0.9037, which is greater than the significance level alpha = 0.05. We can conclude that the observed proportions are not significantly different from the expected proportions.
# printing the p-value
res3$p.value
## [1] 0.9036928
# printing the mean
res3$estimate
## NULL
# Import the data
file_path <- "http://www.sthda.com/sthda/RDoc/data/housetasks.txt"
housetasks <- read.delim(file_path, row.names = 1)
# head(housetasks)
chisq <- chisq.test(housetasks)
chisq
##
## Pearson's Chi-squared test
##
## data: housetasks
## X-squared = 1944.5, df = 36, p-value < 2.2e-16
# Observed counts
chisq$observed
## 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
# Expected counts
round(chisq$expected,2)
## Wife Alternating Husband Jointly
## Laundry 60.55 25.63 38.45 51.37
## Main_meal 52.64 22.28 33.42 44.65
## Dinner 37.16 15.73 23.59 31.52
## Breakfeast 48.17 20.39 30.58 40.86
## Tidying 41.97 17.77 26.65 35.61
## Dishes 38.88 16.46 24.69 32.98
## Shopping 41.28 17.48 26.22 35.02
## Official 33.03 13.98 20.97 28.02
## Driving 47.82 20.24 30.37 40.57
## Finances 38.88 16.46 24.69 32.98
## Insurance 47.82 20.24 30.37 40.57
## Repairs 56.77 24.03 36.05 48.16
## Holidays 55.05 23.30 34.95 46.70
round(chisq$residuals, 3)
## Wife Alternating Husband Jointly
## Laundry 12.266 -2.298 -5.878 -6.609
## Main_meal 9.836 -0.484 -4.917 -6.084
## Dinner 6.537 -1.192 -3.416 -3.299
## Breakfeast 4.875 3.457 -2.818 -5.297
## Tidying 1.702 -1.606 -4.969 3.585
## Dishes -1.103 1.859 -4.163 3.486
## Shopping -1.289 1.321 -3.362 3.376
## Official -3.659 8.563 0.443 -2.459
## Driving -5.469 6.836 8.100 -5.898
## Finances -4.150 -0.852 -0.742 5.750
## Insurance -5.758 -4.277 4.107 5.720
## Repairs -7.534 -4.290 20.646 -6.651
## Holidays -7.419 -4.620 -4.897 15.556
library(corrplot)
## corrplot 0.92 loaded
corrplot(chisq$residuals, is.cor = FALSE)
# Contibution in percentage (%)
contrib <- 100*chisq$residuals^2/chisq$statistic
round(contrib, 3)
## Wife Alternating Husband Jointly
## Laundry 7.738 0.272 1.777 2.246
## Main_meal 4.976 0.012 1.243 1.903
## Dinner 2.197 0.073 0.600 0.560
## Breakfeast 1.222 0.615 0.408 1.443
## Tidying 0.149 0.133 1.270 0.661
## Dishes 0.063 0.178 0.891 0.625
## Shopping 0.085 0.090 0.581 0.586
## Official 0.688 3.771 0.010 0.311
## Driving 1.538 2.403 3.374 1.789
## Finances 0.886 0.037 0.028 1.700
## Insurance 1.705 0.941 0.868 1.683
## Repairs 2.919 0.947 21.921 2.275
## Holidays 2.831 1.098 1.233 12.445
# Visualize the contribution
corrplot(contrib, is.cor = FALSE)
# printing the p-value
chisq$p.value
## [1] 0
# printing the mean
chisq$estimate
## NULL