Biostatistics
Data and distributions, hypothesis testing, p values, confidence intervals, power, sample size and statistical tests.
24 pages
Statistical test
- Analysis of variance (ANOVA)It compares the means of three or more groups at once, in a single test, without inflating the…
- Chi-square testIt compares proportions between groups by measuring how far the observed counts are from those…
- Linear regressionIt fits a straight line that predicts one numerical variable from another
- Logistic regressionIt models a yes-or-no outcome from several variables and gives odds ratios (OR) adjusted for the…
- McNemar testIt compares two proportions measured in the same people (before and after) or in matched pairs
- Non-parametric testsTests that compare groups using the order of the data (ranks) instead of their values, useful…
- Student's t testIt compares two means and says whether the gap between them is larger than chance would explain
Concept
- Choosing a statistical testThe test is chosen with four questions: what type of outcome, how many groups, independent or…
- Hypothesis testingStart by assuming there is no difference, then check whether the data would be rare enough under…
- Multiple comparisonsThe more tests are run, the easier it is for one to come out significant by chance alone
- Non-response, losses and missing dataWhen some participants' data are missing, the result can shift
- Normal distributionThe bell curve: symmetric, with mean, median and mode equal, and fixed shares of the data within…
- P valueThe p value says how surprising the data would be if there really were no difference
- Sample sizeHow many people are needed to detect the effect that matters with the accepted risk of error
- Skewed distributionsWhen data have a long tail on one side, the mean drifts toward the tail and stops describing the…
- Statistical analysis planWriting down, before seeing the data, how they will be cleaned, described and analysed, so the…
- Statistical powerPower is the probability that a study detects an effect that truly exists
- Statistical vs clinical significanceA statistically significant result does not mean it matters to the patient
- Type I and type II errorsType I error: seeing a difference that does not exist (false positive)
- Types of variablesEvery piece of data has a type: unordered categories, ordered categories, counts or measurements
Measure
- Confidence intervalA range of values for the true value that are compatible with the data
- CorrelationIt measures how closely two numerical variables rise or fall together, from −1 to +1
- Measures of centre and spreadMean, median and mode tell where the centre of the data lies; range, interquartile range and…
- Standard errorThe standard error measures how much the mean would vary if the study were repeated on another…
A to Z
← Epidemiology, biostatistics and public health
Educational content on epidemiological and statistical methods; the examples use made-up numbers to teach the calculation. Not a clinical or legal guide: current Colombian rules are in the official sources.
Representative model, for educational purposes only.