1.1 What is Biostatistics?

Learning Objectives By the end of this lesson, the learner will be able to: Define biostatistics in the context of healthcare Explain why biostatistics is essential in clinical and public health practice Recognize how biostatistics appears in everyday healthcare scenarios

What is Biostatistics Quiz?

1.2 Types of Health Data

By the end of this lesson, learners will be able to: Identify the four main types of health data Classify clinical data into appropriate data types Understand why choosing the right data type matters in analysis and research

1.3 Everyday Examples

By the end of this lesson, learners will be able to: Recognize where and how biostatistics appears in everyday healthcare practice Connect key statistical concepts (like average, variability, risk) to real patient care Build confidence in discussing data-based decisions with peers and patients

2.1 Central Tendency

By the end of this lesson, learners will be able to: Define and distinguish between mean, median, and mode Calculate each measure using clinical data Interpret what each tells you in a healthcare setting Understand when to use each one (and why they differ)

2.2 Variability in Data

By the end of this lesson, learners will be able to: Understand what variability means in a health dataset Describe and calculate range, interquartile range (IQR), and standard deviation (SD) Interpret variability in a clinical context (e.g., vital signs, lab results) Recognize why variability matters when making decisions from averages

2.3 Visualizing Data

By the end of this lesson, learners will be able to: Recognize common types of data visualizations used in healthcare Choose the appropriate chart for different data types Interpret bar charts, histograms, and boxplots Understand why visualizing data is critical for effective decision-making

3.1 Populations vs Samples

By the end of this lesson, learners will be able to: Define a population and a sample in health research Understand why samples are used instead of entire populations Recognize the importance of representative sampling Identify sources of sampling bias

3.2 Distributions

By the end of this lesson, learners will be able to: Understand what a distribution is in statistics Recognize common types of data distributions Interpret a normal distribution in a healthcare setting Identify skewed distributions and what they imply for patient care

3.3 Confidence Intervals

By the end of this lesson, learners will be able to: Understand what a confidence interval (CI) represents Interpret CIs correctly in a clinical research context Recognize common misinterpretations of CIs Understand how CIs relate to mean, sample size, and precision

4.1 Hypothesis Testing

By the end of this lesson, learners will be able to: Understand the purpose of hypothesis testing in clinical research Define null and alternative hypotheses Explain what a p-value represents Recognize what statistical significance means (and what it does not mean)

4.2: Common Statistical Tests

By the end of this lesson, learners will be able to: Recognize the most commonly used statistical tests in healthcare research Match the right test to the right type of data and study design Understand what each test is used for and how to interpret its results

4.3 p-values & Significance

By the end of this lesson, learners will be able to: Define a p-value in plain language Understand what statistical significance means Recognize common misinterpretations of p-values Interpret p-values in the context of clinical research

4.4 Creating a Posit Cloud Account & Workspace

By the end of this session, learners will be able to: Create a free Posit Cloud account. Understand the Posit Cloud interface. Set up their first project (workspace). Understand where to write, save, and run R scripts.

4.5a Importing Datasets into Posit Cloud (RStudio in the Cloud)

4.5b Importing Datasets into Posit Cloud (RStudio in the Cloud)

4.6a Exporting Datasets into Posit Cloud (RStudio in the Cloud)

4.6b Exporting Datasets into Posit Cloud (RStudio in the Cloud)

4.7 a Data Cleaning & Exploring Distributions

Checking missing values and duplicates Descriptive stats (psych::describe()) Histograms, boxplots, and density plots (ggplot2) Normality tests (shapiro.test, nortest::ad.test) A small hands-on exercise block for learners

4.7 b Data Cleaning & Exploring Distributions

By the end of this video, you will be able to: Import the demo dataset into R within Posit Cloud. Identify missing values and duplicated records. Generate descriptive statistics to summarize variables. Visualize data distributions with histograms, boxplots, and density plots. Perform normality tests (Shapiro-Wilk, Anderson-Darling) and interpret results.

5.1a One-Sample t-test

The one-sample t-test is useful when testing whether your clinical sample aligns with a standard or guideline threshold. In our case, it answers: Do these 50 patients, on average, differ from the recommended cholesterol level of 200 mg/dL?

5.1b One-Sample t-test

Learning Objectives By the end of this lesson, you should be able to: Recognize when to use a one-sample t-test. Check the normality assumption using the Shapiro-Wilk test and a histogram. Perform a one-sample t-test in R to compare a sample mean with a reference value. Visualize the distribution of data against the reference benchmark. Interpret results in both statistical and clinical terms. Key Takeaway The one-sample t-test allows us to ask: Is my sample’s mean different from a known standard? In our case, the average cholesterol in 50 patients was slightly higher than 200 mg/dL, but the difference was not statistically significant. This demonstrates how statistical tests help distinguish between random variation and meaningful differences in clinical practice.

5.2a Independent -Sample t-test

Imagine 100 hypertensive patients randomized to Drug A or Drug B. Outcome = change in systolic BP from baseline to week 12 (ΔSBP). Research question: Do mean ΔSBP values differ between Drug A and Drug B? Hypotheses: H0: mean(ΔSBP_A) = mean(ΔSBP_B) H1: mean(ΔSBP_A) ≠ mean(ΔSBP_B) Assumptions: Independent groups, approximate normality within each arm, and equal variances (if using Student’s t-test). Analysis: Descriptive stats by arm Shapiro-Wilk test + plots for normality Levene’s test for variances Welch’s t-test (default) or Student’s t-test (if variances equal) Effect size with Cohen’s d Interpretation: Report mean differences, CI, p-value, and clinical significance (e.g., ≥5 mmHg reduction is meaningful). The independent samples t-test allows you to compare mean treatment effects between two groups, combining both statistical significance and clinical relevance.

5.2b Independent -Sample t-test

By the end of this lesson, you will be able to: Define the independent samples t-test and its purpose in comparing two treatment groups. Distinguish between the Student’s t-test and Welch’s t-test: Student’s t-test assumes equal variances across groups. Welch’s t-test does not assume equal variances and adjusts degrees of freedom accordingly. Check assumptions for both tests, including independence, within-group normality, and equality of variances (Levene’s test). Apply the appropriate test based on the variance assumption: Use Student’s t-test if variances are equal. Use Welch’s t-test if variances differ. Interpret the output, including group means, mean difference, confidence intervals, p-values, and effect sizes. Evaluate both statistical and clinical significance when comparing treatment effects.

5.3 a paired t--test