R for Statistical Analysis Schulung

Day One

1. Introduction to R & Rstudio (2 hours)
   • Making R more friendly, R and available GUIs
   • Rstudio
   • Scripting in Rstudio
   • Navigation, sections and code folding
   • Troubleshooting and code debugging in RStudio
   • Related software and documentation
   • Getting help with functions and features
   • Projects in RStudio
   • Creating analytical reports with RStudio
   • Keyboard shortcuts and useful features
2. Importing/Exporting data (1 hour)
   • Flat files – txt, csv
   • Spredsheet files – xls, xlsx
   • SPSS, SAS and other formats data
   • Accessing data from SQL data sources
   • SQL database connectivity and operations
3. Organising data (2 hours)
   • Data types and classes
   • Data storage in R – Rdata format
   • Objects structure
   • Numbers and vectors
   • Matrix and table
   • Factors
   • Lists
   • Data Frames
   • Date and time
4. Tabular representation (3 hours)
   • Overview of packages for data tables – dplyr, tidyr, data.table
   • Indexes and subscripts
   • Selecting, subsetting observations and variables
   • Filtering, grouping
   • Recoding transformations
   • Reshaping data
   • Merging data
   • Character manipulation, stringr package
   • Regular expressions

Day Two

1. Related software and documentation (1 hour)
   • Rstudio and GIT - versioning
   • Markdown
   • Reports and presentations with LaTeX
   • Shiny web applications
2. R and Statistics (2 hours)
   • Probability and Normal Distribution
   • Random numbers
   • Descriptive Statistics
   • Standarization and Normalization
   • Confidence Intervals
   • Hypothesis Testing
   • ANOVA
   • Qualitative data analysis
3. Linear regression (2 hours)
   • Correlation coefficient and interpretation
   • Simple and multiple linear regression
   • Estimation methods – Least squares
   • Model validation – tests for violation of assumptions
   • Selecting variables – different approaches
   • Regulatizations – ridge and lasso regression
   • Generalized least square – nonlinearity
   • Logistic regression
4. Graphical procedures (2 hours)
   • Basic plots for 1 variable
   • Visualizations for 2 and more variables
   • Graphical parameters
   • Special plots
   • Exporting plots to png, pdf and jpeg files
   • Extending graphical capabilities of R with ggplot2
5. Help in R (1 hour)
   • Searching through documentation of R
   • R packages and documentation
   • R Cran Task View – search for problem solution