2024-10-21
<style type="text/css">
body p, div, h1, h2, h3, h4, h5 {
color: black;
font-family: "Modern Computer Roman";
}
slides > slide.title-slide hgroup h1 {
color: #8C1D40; /* the maroon color */
}
h2 {
color: #8C1D40; /* the maroon color */
}
</style>
This is an R Markdown presentation. 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.
Hypothesis testing is a statistical method used to make decisions or inferences about population parameters based on sample data. It helps determine whether the observed effect is statistically significant or occurred by chance.
In hypothesis testing, we compare two hypotheses:
Example: - H₀: The new drug has no effect on recovery time. - H₁: The new drug reduces recovery time.
We test: \[ H_0: \mu_1 = \mu_2 \quad \text{vs.} \quad H_1: \mu_1 \neq \mu_2 \]
Example: In drug testing: - Type I error: Concluding the drug works when it doesn’t. - Type II error: Concluding the drug doesn’t work when it actually does.
Decision Rule: - If p-value < α, reject the null hypothesis. - If p-value ≥ α, fail to reject the null hypothesis.
We reject H₀ when:
\[ p \leq \alpha \] Where α is the significance level, commonly set to 0.05.
Consider a study measuring the effect of two teaching methods on student performance.
Hypotheses: - H₀: The mean score of students is the same for both teaching methods. - H₁: The mean score differs between the two teaching methods.
We can perform a two-sample t-test to determine if there’s a significant difference between the methods.
In this slide, we visualize the normal distribution, which is commonly used in hypothesis testing. The critical region, shaded in blue, represents the range of values where we would reject the null hypothesis. This visualization helps us understand how extreme outcomes (those in the critical region) are unlikely under the null hypothesis and provide evidence for rejecting it.
Hypothesis testing for Test Scores based on study methods
Description of Study Methods:
Group A: Traditional Study Method - Students in Group A followed a traditional study method, focusing on individual learning through textbooks and lecture notes. They studied on their own, without external resources or collaboration.
Group B: Interactive Study Method - Students in Group B used an interactive study method, which involved group discussions, peer collaboration, online tutorials, and video lectures. This method encouraged active learning through multimedia and peer interaction.
ggplot visualization that compares the test scores of two groups of students who used different study methods
# Simulating a dataset of test scores based on study method
set.seed(123)
data <- data.frame(
study_method = factor(rep(c("Group A", "Group B"), each = 50)),
score = c(rnorm(50, mean = 85, sd = 5), rnorm(50, mean = 90, sd = 5))
)
# Creating the boxplot
ggplot(data, aes(x = study_method, y = score, fill = study_method)) +
geom_boxplot() +
labs(x = "Study Method", y = "Test Scores") +
theme_minimal() +
scale_fill_manual(values = c("#D55E00", "#0072B2"))
The boxplot shows that Group B (interactive study method) has higher and more consistent test scores compared to Group A (traditional study method).
While the visualization suggests a difference, further statistical analysis, such as a t-test, is needed to determine if this difference is statistically significant.
Hypothesis Testing:
Null Hypothesis (H₀):
There is no difference in test scores between Group A (traditional study) and Group B (interactive study).
Alternative Hypothesis (H₁):
There is a significant difference in test scores, with Group B expected to perform better due to the interactive method.
This suggests that the interactive study method (Group B) results in higher average scores than the traditional method (Group A).
## ## Welch Two Sample t-test ## ## data: score by study_method ## t = -6.0718, df = 97.951, p-value = 2.406e-08 ## alternative hypothesis: true difference in means between group Group A and group Group B is not equal to 0 ## 95 percent confidence interval: ## -7.377243 -3.742805 ## sample estimates: ## mean in group Group A mean in group Group B ## 85.17202 90.73204
Weight Differences by Gender
In this case, we are comparing the weight distributions of males and females to determine if there is a statistically significant difference between the two groups.
Null Hypothesis (H₀): The average weight of males and females is the same.
Alternative Hypothesis (H₁): There is a significant difference in the average weight between males and females.
The boxplot is useful for visually assessing the distribution and spread of weights for both genders.
The boxplot shows the weight distribution for males and females. The median weight for males appears to be higher than that for females, with a wider spread of data. This suggests that males generally weigh more than females, but further statistical testing is needed to confirm if this difference is significant.
Null Hypothesis (H₀): There is no significant difference in the average weight between males and females.
Alternative Hypothesis (H₁): There is a significant difference in the average weight between males and females.
## ## Welch Two Sample t-test ## ## data: weight by gender ## t = -5.5175, df = 92.636, p-value = 3.104e-07 ## alternative hypothesis: true difference in means between group Female and group Male is not equal to 0 ## 95 percent confidence interval: ## -12.474308 -5.871231 ## sample estimates: ## mean in group Female mean in group Male ## 61.17127 70.34404
we can reject the null hypothesis and conclude that the difference in weights is statistically significant.