Computing Monte Carlo Standard Error for an arbitrary function

Abierto
  • ¿Algo no está bien?
#57 10 comentarios 0 reacciones 1 asignado Ver en GitHub

@MansMeg ya está trabajando en esto.

Desde el 3/1/2020.

Evaluación

Este issue todavía no se ha evaluado.

Descripción

feature

Hi!

Me, @paul-buerkner and @avehtari discussed the need for computing the MCSE for different functions of interest, such as the marginal variances, skewness and kurtosis of individual parameters. I think this functionality is probably best to implement directly into the posterior package. Aki suggested to use the batch means and subsampling approaches of https://projecteuclid.org/download/pdfview_1/euclid.ejs/1417615759 and I could implement this into posterior since I need to implement it anyway.

The most important part for me to know is how you would like the API to look. This is my first suggestion, feel free to comment or come up with a better suggestion.

monte_carlo_standard_error(x, FUN = mean)

where x is a draws object and FUN is an arbitrary function that operates on the individual parameters (rv?) of the draws object. It returns an object similar to summary() but with column with the names:
[parameter_name]_[function_name] and [parameter_name]_[function_name]_se

Any thoughts or comments before I get started?

Lenguaje dominante
R
Estrellas
172
Forks
27
Merge medio
5 d 12 h
PR fusionados (30 d)
5

Preparar el entorno

Primeros pasos

  1. Lee el issue completo y luego la guía de contribución del proyecto.
  2. Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
  3. Haz un fork del repositorio y trabaja en una rama.
  4. Abre un pull request que haga referencia al número del issue.

Más de stan-dev/posterior

Todos los issues de stan-dev/posterior

Issues similares

Más issues de R

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.