Course outline
Getting started with R, R studio, and R Studio cloud.
Inroduction to the alternative GUIs:
- Rcmdr
- Jamovi
- JGR
- Deducer
- Blusky
Basic operations
- Connecting to a working directory.
- Customising the interface.
- Understading the basic operators
- Data types (integer, double, logical, character )
- Loading and using example dataframes
- Creating toy datasets
- Reading comma-separated values (CSV) files, tab-separated values (TSV) files, fixed-width files.
- Importing datasets.
Using packages
- Installation
- Loading
- Installing and loading several packages simultaneously
- Unload packages without restarting R
- Dealing with conflicting packages
Learning the essential R packages
- rio (R input Output)
- dplyr (dataframes pliers)
- psych (Procedures for Psychological, Psychometric, and Personality Research)
- lavaan (latent variable analysis)
- extensible markup language (XML)
- caret (classification & regression training)
- stargazer (exporting regression and summary tables)
- car (companion to applied regression)
- rms (regression modeling strategies)
- sgm (stochastic gradient methods)
- ggplot (grammar of graphics)
Data wrangling
- Handling missings and outliers (imputation)
- Renaming columns
- Recoding columns
- dplyr functions (filter, distinct, slice, arrange, select, pull, mutate)
- Join types (inner join, left join, right join, full join, semi join, anti join)
Dataframe functions
- Using tibbles and data.table
- Reshaping (long to wide, wide to long)
- Subsetting and merging dataframes (rbind, cbind)
- Subsetting by column types (string/ factor)
- Transposing rows and columns
- Merging rows and columns
Basic summary Statistics with visualization
- Bar Graph
- Pie Chart
- Histograms
- Boxplots
Summary tables
- Reporting basic statistics with Hmisc and psych
- Reporting prcentages with tabyl (janitor)
- Summarising continuous vars with epidisplay
- Cross-tabs of categorical cars with gmodels
Regression analysis
- Finding the best predictors (leap, glmulti)
- Linear regression (Simple vs Multiple vs Polynomial)
- Generalized Linear Model
- Multinomial logistic regression
- Generalized estimating equations
- Regression for categorical response variables
- Variable importance analysis
- Model diagnostics
- Regression plots (Forest plot)
- SEM and path analysis with lavaan
Making reports with R
- R Markdown