• “Tidy Data” concept
• Common data file types
• Excel, data setup, and the Data Dictionary
• Getting data into R
• Manipulating variables
• Practice exercises

The data should be in a standard, accessible, reproducible, non-haphazard, format

• One column per variable

• One row per observational unit

• Thought given to sympathetic data “codification”

• explanation of variables

• Variable naming conventions

Delimited text files

• .csv, .txt, tab-delimited, others

• first row with variable names

• problem with explanation of variables

Excel is okay, but must be Tidy

Avoid proprietary formats (like SPSS, Genstat, etc.)

Different data file types require different functions

for .csv read.csv()

for other delimited read.table()

for Excel library(openxlsx); read.xlsx()

many others exist

• names() function

• The use of the $ operator for data frames

• The use of the str() function for data frames

• The use of the index operator [ , ]

• The use of the attach() function