Sample Data

# Load necessary libraries
set.seed(42)
n <- 50
numeric_variable <- rnorm(n, mean = 100, sd = 15)
paired_sample1 <- rnorm(n, mean = 100, sd = 10)
paired_sample2 <- rnorm(n, mean = 95, sd = 10)
group1 <- rnorm(n, mean = 100, sd = 15)
group2 <- rnorm(n, mean = 95, sd = 15)
categorical_variable <- rbinom(n, size = 1, prob = 0.4)
group1_binary <- rbinom(n, size = 1, prob = 0.3)
group2_binary <- rbinom(n, size = 1, prob = 0.5)

# Create data frame
data <- data.frame(
  numeric_variable,
  paired_sample1,
  paired_sample2,
  group1,
  group2,
  categorical_variable,
  group1_binary,
  group2_binary
)

head(data)
##   numeric_variable paired_sample1 paired_sample2    group1    group2
## 1        120.56438      103.21925      107.00965  99.38952  64.98606
## 2         91.52953       92.16161      105.44751  76.72683 100.00666
## 3        105.44693      115.75728       84.96791 117.50754 112.56988
## 4        109.49294      106.42899      113.48482  95.89531 125.89309
## 5        106.06402      100.89761       88.33227  92.98232  74.34708
## 6         98.40813      102.76551       96.05514  81.42622  77.73717
##   categorical_variable group1_binary group2_binary
## 1                    0             1             0
## 2                    0             0             0
## 3                    0             0             1
## 4                    1             0             0
## 5                    0             0             1
## 6                    1             0             0

1. One-Population Mean Test (Unknown Sigma)

one_population_mean_test <- t.test(data$numeric_variable, mu = 100)
print(one_population_mean_test)
## 
##  One Sample t-test
## 
## data:  data$numeric_variable
## t = -0.21906, df = 49, p-value = 0.8275
## alternative hypothesis: true mean is not equal to 100
## 95 percent confidence interval:
##   94.55623 104.37361
## sample estimates:
## mean of x 
##  99.46492

2. Two-Population Mean Paired Test (Unknown Sigma)

two_population_paired_test <- t.test(data$paired_sample1, data$paired_sample2, paired = TRUE)
print(two_population_paired_test)
## 
##  Paired t-test
## 
## data:  data$paired_sample1 and data$paired_sample2
## t = 4.0495, df = 49, p-value = 0.0001823
## alternative hypothesis: true mean difference is not equal to 0
## 95 percent confidence interval:
##   3.787905 11.251145
## sample estimates:
## mean difference 
##        7.519525

3. Two-Population Mean Independent Test (Unknown Sigma)

two_population_independent_test <- t.test(data$group1, data$group2, var.equal = FALSE)
print(two_population_independent_test)
## 
##  Welch Two Sample t-test
## 
## data:  data$group1 and data$group2
## t = 1.6081, df = 96.828, p-value = 0.1111
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -1.059931 10.110245
## sample estimates:
## mean of x mean of y 
##  99.64426  95.11910

4. One-Population Proportion Test

successes <- sum(data$categorical_variable)
n_total <- nrow(data)
prop_test_one <- prop.test(successes, n_total, p = 0.5, alternative = "two.sided")
print(prop_test_one)
## 
##  1-sample proportions test with continuity correction
## 
## data:  successes out of n_total, null probability 0.5
## X-squared = 4.5, df = 1, p-value = 0.03389
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
##  0.2159464 0.4885541
## sample estimates:
##    p 
## 0.34

5. Two-Population Proportion Test

successes_group <- c(sum(data$group1_binary), sum(data$group2_binary))
sizes_group <- c(length(data$group1_binary), length(data$group2_binary))
prop_test_two <- prop.test(successes_group, sizes_group, alternative = "two.sided")
print(prop_test_two)
## 
##  2-sample test for equality of proportions with continuity correction
## 
## data:  successes_group out of sizes_group
## X-squared = 2.0798, df = 1, p-value = 0.1493
## alternative hypothesis: two.sided
## 95 percent confidence interval:
##  -0.36766591  0.04766591
## sample estimates:
## prop 1 prop 2 
##   0.30   0.46