1st Semester

This introductory module in Biostatistics aims to familiarize students with fundamental biostatistical concepts and reasoning. Important learning outcomes include recognizing and measuring variability and uncertainty, distinguishing data types, describing central tendency and dispersion in data, forming and testing statistical hypothesis on population means and proportions, describing error types, and interpreting correlation and regression statistics.  While there are some basic formulae and computations in the course, the emphasis is on statistical thinking, critical reasoning and interpretation. Examples and applications with statistical software on mostly real world data are also given. 

• Distinguish between different types of data in public health and medical research studies.
• Describe different types of study designs, including different sampling methods.
• Interpret differences in data distributions using statistical plots and graphs.
• Distinguish between populations and samples, parameters and statistics, standard errors and standard deviations.
• Describe the normal distribution and its properties.
• Explain the concept of a sampling distribution.
• Compute and interpret confidence intervals for population means and proportions.
• Define the concepts of null hypothesis, significance testing and statistical significance.
• Interpret and explain a p-value.  
• Distinguish between statistical significance and clinical (practical) significance.
• Perform independent and paired t-tests and interpret the results.
• Calculate a confidence interval for the difference in population means or proportions.
• Be aware of non-parametric alternatives for hypothesis testing. 
• Perform chi-square and McNemar’s tests for proportions and interpret the results.
• Define type I and type II error rates in hypothesis testing and explain their practical implications in research.
• Calculate and interpret risk differences (absolute risks), risk ratios (relative risks) and odds ratios.
• Interpret correlation coefficients and scatter plots.
• Perform simple linear regression for quantifying correlations and making predictions.
• Interpret the results of multiple linear regression.
• Use the Epi Info statistical software (CDC) to perform descriptive and inferential statistical analyses.

Recommended textbooks:

• Practical Statistics for Medical Research D.G. Altman, 1991.
  
• Medical Statistics A Textbook for the Health Sciences 5th ed. D. Machin, MJ Campbell & Walters, 2021.