Methods for comparing the average values of three or more groups in R, including one-way ANOVA and related tests. ANOVA is a way to assess whether group means differ beyond what random variation might explain.
A set of R methods for comparing categorical data, such as counts, rates, or group memberships. It covers chi-square tests, Fisher's exact test, McNemar's test for paired data, stratified tests, and goodness-of-fit tests.
An R-language medical statistics skill for the Cochran–Armitage trend test. This test checks whether a two-outcome result changes in a roughly linear direction across ordered groups, such as increasing drug doses.
A set of R methods for measuring and modelling the relationship between two continuous variables. It covers Pearson and Spearman correlation, simple linear regression, R², and curve fitting.
A set of R-language guidance for discrete probability distributions, which describe countable outcomes such as events occurring a certain number of times. It covers binomial and Poisson distributions, probability calculations, and goodness-of-fit tests in medical settings.
A set of R tests that compare groups without requiring the data to follow a normal distribution. It includes Wilcoxon tests, the Mann–Whitney U test, Kruskal–Wallis test, and Friedman test.
An R-language guide for creating random assignment plans in clinical trials, where participants are assigned to treatment groups by chance. It covers simple, stratified, and block randomization.
An R-language guide to ROC analysis, a way to assess how well a diagnostic test distinguishes between two outcomes. It covers the area under the curve (AUC), sensitivity, specificity, predictive values, AUC comparison, and the best cutoff value.
An R-language guide to estimating how many participants a study needs, using the pwr package. It covers t-tests, analysis of variance, chi-square tests, correlation, and comparisons of proportions.
An R-language medical statistics skill for making basic statistical charts. It covers histograms, box plots, scatter plots, bar charts, error-bar charts, stem-and-leaf plots, P–P plots, and Q–Q plots.
R-based tables that summarise the starting characteristics of study groups, often called a baseline table or Table 1. They can show continuous and categorical variables in a three-line format used by many Chinese-language journals.
A group of R methods for comparing means in one or two groups. It includes one-sample, paired, and independent-samples t-tests, plus checks for normality and equal variances.
Use when the user asks to create, scaffold, or edit Jupyter notebooks (.ipynb) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script newnotebook.py to generate a clean starting notebook.
An R-based method for studying survival data when one type of event can prevent another from happening. It estimates the chance of each event over time using the Fine–Gray model and cumulative incidence functions.
Statistical methods for testing whether effects change across ordered groups or with an interaction between variables. They also report the effect of a one-standard-deviation increase, where a standard deviation measures typical spread in the data.
A regression method that adds squared or cubed terms to model curved relationships between variables. It can fit and compare second- and third-degree polynomial models.
A way to pair people in an observational study who have similar propensity scores, meaning similar estimated chances of receiving a treatment. Matching can be one-to-one or one-to-many.
Ways to use a propensity score as a regression variable or to divide people into score-based groups. A propensity score is the estimated chance that a person receives a treatment based on measured characteristics.
A way to use propensity scores to weight people in an observational study. The weights create a modelled population in which the measured characteristics of comparison groups are more balanced.
An R workflow for restricted cubic spline regression, a method for modeling curved rather than straight relationships between a variable and an outcome. It uses the rms package to fit and test these curves.
An R workflow for medical subgroup analysis, which compares results separately across groups such as sex or age. It also creates forest plots, charts that show estimated effects and their uncertainty.
An R guide for choosing between two medical forest-plot analyses. Subgroup analysis fits separate models within groups, while multivariable regression compares categories within one model after accounting for other variables.
An R workflow for running subgroup analysis with one command. It uses the jstable package to estimate effects and create forest plots for several groups, with support for Cox, logistic, and survey-weighted models.
★not rated 12 1mo agoA140 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: