This page collects links to tutorials and other online resources we have found useful for SCS clients.
Graphical methods
- Royal Statistical Society Best Practices for Data Visualisation. Insights, advice, and examples (with code) to make data outputs more readable, accessible, and impactful.
- Twenty rules for good graphics. This post by Rob Hyndman, describes some best practices for producing graphs for journal publication.
- British Ecological Society’s Guide to Reproducible Science. The guide proposes a simple reproducible project workflow, and a guide to organizing projects for reproducibility. The Programming section provides concrete tips and traps to avoid (example: use relative, not absolute pathnames), and the Reproducible Reports section provides a step-by-step guide for generating reports with R Markdown.
Multiplicity Control
https://www.youtube.com/watch?v=HpjlcEH4zuY
Negligible Effect (Equivalence) Testing
Using significance tests to evaluate equivalence between two experimental groups. Equivalency testing, a statistical method often used in biostatistics to determine the equivalence of 2 experimental drugs, is introduced to social scientists. Examples of equivalency testing are offered, and the usefulness of the method to the social scientist is discussed.
Lakens et al. Equivalence Testing for Psychological Research: A Tutorial
- Introduction to Equivalence Testing with TOSTER describes the
TOSTERpackage. - The
neglibiblepackage provides functions that are useful for conducting negligible effect testing (also called equivalence testing),
including equivalence of means or the presence of a negligible association (correlation or regression)
https://www.youtube.com/watch?v=AEpMHDXK8UI
Linear models (ANOVA, Regression)
- Overview of R Modelling Packages. An overview of R packages and functions for fitting different types of linear models, classified by the type
of outcome variable (continuous, binary, catgegorical). Contains links to examples and shows Bayesian equivalents of many frequentist approaches. - Data and Model Summaries in R.
modelsummaryis an R a package to summarize data and statistical models in R. It supports over one hundred types of models out-of-the-box, and allows users to report the results of those models side-by-side in a table, or in coefficient plots. There is also a JSS paper that condenses many examples into a shorter format.
Meta Analysis
- Mathais Harrer Doing Meta Analysis in R. An accessible introduction into how meta-analyses can be conducted in R. Essential steps for meta-analysis are covered, including pooling of outcome measures, forest plots, heterogeneity diagnostics, subgroup analyses, meta-regression, methods to control for publication bias, risk of bias assessments and plotting tools.
Structural Equation Models
- How to Conduct Power Analysis for Structural Equation Models: A Practical Primer
pwrSEM is a Shiny web app that researchers can use to conduct power analysis for structural equation models. Tutorial papers for pwrSEM can be found at: https://journals.sagepub.com/doi/full/10.1177/2515245920918253;
Effect size & power analysis
- Matthew B Jane et al. Guide to Effect Sizes and Confidence Intervals. This guide aims to provide academics, students and researchers with hands-on, step-by-step instructions for calculating effect sizes and confidence intervals for common statistical tests used in the behavioral, cognitive and social sciences.
- Metin Bulus Statistics Power Analysis and Sample Size Calculation Tools. An online shiny application with power / sample size calculators for a wide variety of statistical problems.
Latent Profile Analysis
Latent profile analysis (LPA) is a latent variable method that focuses on identifying latent sub-populations within a population based on observed variables.
LPA works best with continuous variables (and, in some cases, ordinal variables), but is not appropriate for dichotomous (binary) variables.
- Spurk et al. Latent profile analysis: A review and “how to” guide of its application within vocational behavior research
- Introduction to tidyLPA. The
tidyLPApackage provides an interface to the powerful and widely-used mclust package for Gaussian Mixture Modeling. - Quick Example of Latent Profile Analysis in R