Advanced Biostatistics
Clinical research statistics for medical students
You have taken introductory biostatistics. This site picks up from there: what the statistics section of a clinical paper is actually doing, and how to run it yourself.
Start from a study design
Which statistics each design uses, how to read its tables and figures, and the traps specific to it.
- How to read a clinical research paperA paper is not read front to back. This chapter gives a reading order, the question to ask at each stop, and a lookup table from "what you just saw" to "the page that explains it".
- Cohort studyWhere the line between prospective and retrospective actually falls, why an observed association is not a treatment effect, and how to write up a result that did not reach statistical significance without fooling yourself.
- Case-control studyWhy a case-control study yields an odds ratio and never an incidence rate, what matching actually buys, and how one real analysis nearly credited the right finding to the wrong cause.
- Randomised controlled trialWhat the statistics section of an RCT is doing, how to read one in order, and the parts textbooks rarely cover but real trials always have — interim analyses, early stopping, and the patient who was counted anyway.
- Diagnostic accuracy studySensitivity and specificity are properties of a test, but the numbers you get depend on whom you enrolled and whom you verified — this chapter uses live figures to show two ways a good test is made to look better, and why the same test reports a sensitivity three times higher in one ward than another.
- Prediction model studyA prediction model does not ask which variable is associated with the outcome; it asks what this person's risk is — and that switch changes what counts as passing. This chapter walks through a real external validation where discrimination barely drops while calibration goes systematically wrong.
- Database studies and real-world dataA national claims database does not exist for research; it exists for reimbursement. This chapter covers what that gap costs you, the limits specific to Taiwan's NHIRD, and a seven-rung worked example — including the rung that lands on the right answer by the wrong method.
- Systematic review and meta-analysisWhy a systematic review and a meta-analysis are not the same thing, what each box of the PRISMA flow diagram is defending against, why "the search returned nothing" and "nothing survived screening" must never be written as one sentence, and how a result that exists only inside a figure can push a whole review's conclusion off course.
Start from a method
One page per method: the idea, when to use it, how to read the output, R and Python code, and common misuses.
- Table 1 and standardised mean differences
- t-tests and analysis of variance
- Chi-square test and Fisher's exact test
- Non-parametric tests: Wilcoxon and Kruskal-Wallis
- Distribution plots, and the dynamite plot
- Linear regression
- Logistic regression and the odds ratio
- Poisson and negative binomial regression
What you can read so far
This map reads only the questions you have answered on this device. A node lights when every page under it has at least one answer and your first-attempt accuracy clears the threshold.
Level 10 XP405 questions
This browser has local storage switched off, so answers are not remembered. The map still works.
Methods
- B1Description and testing30 questionsNot yet litNo answers yet
- B2Regression39 questionsNot yet litNo answers yet
- B3Survival analysis27 questionsNot yet litNo answers yet
- B4Diagnostic accuracy30 questionsNot yet litNo answers yet
- B5Prediction models59 questionsNot yet litNo answers yet
- B6Causal inference62 questionsNot yet litNo answers yet
- B7Evidence synthesis48 questionsNot yet litNo answers yet
- B8Cross-cutting issues44 questionsNot yet litNo answers yet
- B9Agreement and reliability18 questionsNot yet litNo answers yet
Study designs
- DStudy designs48 questionsNot yet litNo answers yet
How this site is written
- Every figure is real output from a public dataset, with copy-pasteable R and Python code and the path of the script that produced it.
- Every example dataset ships inside an R package and is one line away — no data access application required.
- Terms carry both English and Chinese, searchable in the glossary.
- Content is CC BY-SA 4.0. Passages adapted from other open material name their source and licence in the page footer.