Home - Private-Projects237/Statistics GitHub Wiki

Welcome to the Statistics wiki!

Below are descriptions of different statistical approaches and the code for them in R.

T-test

• Overview of the Standard t-test: Standard t-test Overview

Converting test statistics to effect sizes

• This will cover how to calculate cohen's D from test statistics. This is very useful for papers that do not directly report means and standard deviations: Converting test statistics to Cohen's D
• This will cover how to calculate partial eta-square from test statistics. This is very useful for papers that do not directly report means and standard deviations: Converting test statistics to partial eta square from ANOVA
• Here we will also calculate partial eta-square from test statistics- specifically from repeated measures ANOVA: Converting test statistics to partial eta square from repeated measures ANOVA
• Read this one extracting effect size correctly from ANOVAS, with a focused on the most common ones which are mixed ANOVAS: Converting test statistics to partial eta squared and generalized eta squared

Regression

• Overview of Regression: Regression Overview

Regression and Effect Size

• An overview that focuses on simple and multiple regression and how to calculate effect sizes Regression and Effect Sizes

Logistic Regression

• Overview on Logistic Regression: Logistic Regression Overview
• More Logistic Regression from the 'Extending the Linear Model with R' textbook Extending the Linear Model with R: Chapter 2 Logistic Regression

Gamma Regression

• Information related to running a Gamma Regression in R: Gamma Regression in R

ANOVA

Underlying Math

• This will produce a step by step guide on what the math behind a one-way ANOVA is: Math Underlying a one-way ANOVA
• This will produce a step by by step guide on what the math behind a one-way repeated measures ANOVA is: Math Underlying a one-way repeated measures ANOVA
• This will produce a step by step guide on what the math behind a two-way ANOVA is: Math Underlying a two-way ANOVA

Interpreting Outputs

• Interpreting the outputs of a one-way repeated measures ANOVA: Interpreting the Outputs in a One-Way Repeated Measures ANOVA

ANCOVA

• Overview of analysis of covariance (ANCOVA): ANCOVA Overview

Effect Coding

• Information related to effect coding in R: Effect Coding in R
• Effect Coding and Estimated Marginal Means in R: Effect Coding and Estimated Marginal Means in R

Estimated Marginal Means

• Information related to estimated marginal means for factors in R: Estimated Marginal Means in R
• This next section is on estimated marginal means from custom contrasts in R: Estimated Marginal Means from Custom Contrasts in R

Plotting Main Effect and Estimated Marginal Means Follow-Up Tests (Asterisk Lines)

• The code and example to create graphs with the asterisk lines from your own p-values: Plotting Asterisk Lines in Follow-Up Tests

Estimated Marginal Means of Linear Trends (Slopes)

• Information related to obtaining the slopes of continuous v factor interactions in R Estimated Marginal Means of Linear Trends in R

Mediation Analysis

• This will be an introduction into mediation analysis using examples inspired by the stress, testosterone, and cognition meta Introduction into Mediation Analysis

Meta-Analysis

• Here we will be describing meta-analysis in accordance to 'Doing Meta-Analysis in R: A Hands on Guide' Meta Analysis in R
• Calculating means and standard deviations when they are not presented: Estimating means and standard deviations
• Comparing fixed effects vs random effects meta-analysis models in R: Meta Analysis Fixed Effects vs Random Effects Models
• Running moderation analyses in a meta-analysis with heterogenous data: Testing for Moderation in a Meta Analysis
• Running a multilevel meta analysis in R: How to run a multi level meta analysis in R

Path Analysis

• In depth introduction into path analysis in R: Introduction to Path Analysis Using Lavaan
• Doing a path analysis on simulated data that represents an ONR project. There are several examples here that build on complexity that detail direct, indirect, mediation, and interaction effects with continuous variables only: Intermediate Path Analysis Examples in R

Linear Mixed Effects Models

• Template 1 to use: Linear Mixed Effects Models (Behavior Example)
• Template 2 to use: Linear Mixed Effects Models (ERPs Example).
• Here are examples to different cases where linear mixed effects models should be used: Introduction into when to use Linear Mixed Effects Models
• Pretty in depth look into how to specify linear mixed effects models in R using lme4: lme4: Mixed-effects modeling in R

Quadratic Linear Mixed Effects Models

• Modeling predictors as quadratic: Quadratic Linear Mixed Effects Models

Generalized Linear Mixed Effects Models

• Intro into linear mixed effects models GLMM Intro into Linear Mixed Effects Models
• Intro into generalized linear mixed effects models Intro into Generalized Linear Mixed Effects Models GLMM

Generalized Structural Equation Modeling (GSEM)

• Here we will cover specific examples of how to run generalized structural equation modeling to predict a dichotomous outcome from several predictors while introducing a mediation analysis: GSEM for Path Analysis and Nested Logistic Regression

Multivariate Mixed Effects Models

Introduction into running multivariate mixed effects models: Intro into Multivariate Mixed Models

Power Analyses

• Introduction to doing a power analysis on mixed effects models through simr: Introduction to Power Analysis Using simr for Mixed Models
• Introduction to doing a power analysis on linear mixed-effects models: Introduction into Power Analysis for Linear Mixed-Effects Models

Confirmatory Factor Analysis (CFA)

• Introduction into Confirmatory Factor Analysis using Lavaan: Confirmatory Factor Analysis with Lavaan
• Heywood Cases and Constraining Introduction: Introduction into Heywood Cases and Consequences of Constraining

Item Response Theory (ITR)

• This is information covering IRT to estimate subject performance on an assessment Two parameter IRT model (2PL)
• This is information covering IRT to estimate subject performance on an assessment across datasets with different types of missing data Two parameter IRT model (2PL) with Missing Data
• This will be exploring the theta values and comparing them to z-scores in a well generated dataset: Exploring the Theta Estimate in the IRT model (2PL)
• This will be exploring the IRT Graded Response Model (GRT), which is great at handling datasets that have more than two values if there is an ordinal structure to it: Graded Response Model (GRT)

Path Diagrams

• This is information from a YT video Path Diagrams for some common types of statistical models

SEM

• This page will contain an overview of the HolzingerSwineford1939 dataset Higher order factor model HolzingerSwineford1939

Complex Models

• This page will be used strictly to test the capabilities of a bayesian generalized (non)-linear multivariate multilevel model: Testing the Capabilities of a Bayesian Non Linear Multivariate Multilevel Model in R
• This page will cover how to capture direct and indirect effects using Bayesian statistics: Capturing Direct, Indirect, and Mediation Effects with Bayesian Statistics

Categorical Exploratory Factor Analysis (EFA)

• This page will be discussing how to run categorical exploratory factory analysis (EFA) using the lavaan syntax: Getting Started with Categorical with Exploratory Factor Analysis (EFA) in Lavaan

Categorical Confirmatory Factory Analysis (CFA)

• This page will use a basic categorical confirmatory factory analysis example. This will function as a good introductory into the concept: Getting Started with Categorical Confirmation Factor Analysis
• Here we will show an example of a hierarchical categorical confirmatory factory analysis. This will function as a good introductory into the concept: Hierarchical Categorical Confirmation Factor Analysis
• For this page we will explicitly cover invariant and non-invariant conditions in categorical CFA: Invariant and Non-Invariant categorical CFA