Saltar al contenido ForoHackers

R: start here

R
#3087 · · Citar · Denunciar

R is a language and environment for statistics, data analysis and graphics. It was made by statisticians, so data frames, models, tests and plots are built in or a package away. It is used in research, epidemiology, finance and anywhere results must be reproducible, and its interactive workflow suits exploring data and writing reports.

Key concepts

  • Vectors: the basic type; even a single number is a vector, and operations apply to all elements.
  • Data frames: tables of columns with different types, the core structure of analysis.
  • Functional style: functions are values, and apply-family functions replace most loops.
  • Formulas and models: a compact syntax describes a model, such as regression, and fitting returns an object to inspect.
  • Packages: a large repository of statistical methods and data tools, installed per project.
  • Reproducible reports: documents that mix prose, code and results, regenerated on demand.

Vocabulary

  • Factor: a categorical variable with a fixed set of levels.
  • NA: the marker for a missing value, which propagates through calculations.
  • Tidy data: one variable per column, one observation per row.
  • Notebook or report: a document executed to produce its figures and tables.

What to study, in order

  1. Vectors, indexing, functions and the console; compute summary statistics by hand.
  2. Data frames: import a file, clean it, filter, group and summarise.
  3. Plot distributions and relationships, and judge what each chart does and does not show.
  4. Fit and interpret a linear model, and check its assumptions.
  5. Write a reproducible report that regenerates every figure from the raw data.
  6. Learn the basics of writing your own function and package.

Related tags

#data-science #data-visualization #probability #research-software

No has iniciado sesión, así que esto se publica como anónimo: no se guarda con ello ninguna cuenta, nombre ni dirección, y no puede llevar enlaces ni imágenes. Inicia sesión o únete para publicar con tu nombre. Los registros de nuestro servidor web guardan la dirección y la hora de cada petición hasta 14 días; para que la tuya no quede en ellos, usa Tor. Para escribir al equipo de forma confidencial, usa el buzón. Firmar como fuente habitual (una clave guardada solo en este navegador)

Enviar tarda unos segundos aquí: tu navegador resuelve antes una prueba de trabajo contra el spam.

Responder