This 2.5 day workshop is intended to leave participants up and running with the R statistical software. It is an attempt to provide the solid foundation needed to begin using R in your data analysis and statistical needs. No previous experience is required, though some basic programming or data science experience is helpful.
- data types, vectors, matrices, strings, factors
- control structures (for, if else, while)
- functions, R markdown
- basic plotting
- computing with probabilities and distributions
- Performing descriptive statistics
- Basic statistical tests (t-tests, single regression, correlation, ANOVA, logistic regression)
- data manipulation
- Data visualization with ggplot2
Options:
- Packages for faster data manipulation (dplyr, data.table)
- Panel data
- Interactive javscript based plots
- time series
- Logistic regression
- trees
The workshop will contain plenty of hands-on, interactive explorations of real data sets with relevant spatial and temporal information.
You should install the R language and its popular IDE RStudio prior.
When you start RStudio you should see 3 panels, one of them the Console where you can type commands.
#mandatory
install.packages(c("knitr", "markdown", "rmarkdown","ggplot2", "dplyr","swirl", "RgoogleMaps", "nycflights13", "stringr", "ISLR", "tseries"), dependencies = TRUE)
#nice-to-have
install.packages(c("dygraphs", "AER", "plm", "nlme"), dependencies = TRUE)I would decline the compilation from source.
Be prepared to wait a while, lots of dependent packages are being installed as well.
Now download the swirl course Baruch_day1.zip to a directory on your computer.
After this, load the swirl library and install this course:
library(swirl)
install_course_zip(file.choose())