Biostatistics and epidemiology
Sensitivity and specificity, predictive values and prevalence, relative risk and odds ratios, ARR, RRR and NNT, study designs, bias, type I and II errors and power, and confidence intervals.
5:34Sensitivity vs specificity: the 2×2 table, SnNout and SpPin
How to calculate sensitivity and specificity from a 2×2 table, and why a highly sensitive test rules disease out while a highly specific test rules it in.
5:27PPV, NPV and prevalence explained
A test can be 90% sensitive and 90% specific and still be wrong most of the time when it says positive, if the disease is rare. With the test fixed, prevalence moves the predictive values.
5:15Relative risk vs odds ratio: the 2x2 table explained
One 2x2 table can give a relative risk of 4 and an odds ratio of 4.75. Learn how to calculate each, why they differ, and which one a cohort or case-control study can report.
5:00Number needed to treat: ARR, RRR and NNH from trial data
A headline can say a drug halves the risk while 100 patients must be treated for five years to prevent one event. Absolute and relative figures answer different questions.
5:22Study designs explained: case-control, cohort, cross-sectional and RCT
Three questions sort the main study designs: was the exposure assigned, is there a comparison group, and were people picked by exposure or by outcome. Then name the measure each design gives.
5:30Types of bias: selection, recall, lead-time and confounding
Bias is systematic error that pushes a result in one direction. Learn the three families, why screening can raise survival without changing deaths, and the step that reduces each bias.
5:16Type I and type II errors: alpha, beta, power and the p-value
A type I error rejects a true null hypothesis; a type II error misses a real effect. Learn how alpha, beta, power and the p-value fit together, and what raises power.
5:12Confidence intervals and significance: is the null value inside?
A confidence interval is a range built to capture the true value. Check whether it includes the null value, and you can judge significance and precision at a glance.