Universidad Galileo

Introducción

El dataset de Anscombe sirve para ejemplificar la importancia de graficar los datos.

Anscombre usó este dataset para demostrar que las estadísticas puntuales no son suficientes para describir la data.

Esto es una cita.

Descripción del Dataset

Tabla de medias del cuarteto de anscombe

estadistico \(x_1\) \(x_2\) \(x_3\) \(x_4\)
Medias 9 9 9 9
Desviacion 3.3166248 3.3166248 3.3166248 3.3166248
Medianas 9 9 9 8
estadistico \(y_1\) \(y_2\) \(y_3\) \(y_4\)
Medias 7.5009091 7.5009091 7.5 7.5009091
Desviacion 2.0315681 2.0316567 2.0304236 2.0305785
Medianas 7.58 8.14 7.11 7.04

Preparación de la data para la gráfica

anscomb_tidy <-
rbind(
data_frame(x = anscombe$x1, y = anscombe$y1, tag = "q1"),
data_frame(x = anscombe$x2, y = anscombe$y2, tag = "q2"),
data_frame(x = anscombe$x3, y = anscombe$y3, tag = "q3"),
data_frame(x = anscombe$x4, y = anscombe$y4, tag = "q4"))

Plot

anscomb_tidy %>% 
  ggplot(aes(x,y)) + 
  geom_point() +
  geom_point() +
  facet_wrap(~tag,ncol = 2)

Conclusiones

  1. Las gráficas todas tienen las mismas medias.
  2. Todas tienen la misma desviación estandar.
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