README.md

hilo

Travis-CI Build
Status Coverage
Status CRAN_Status_Badge

A simple class for ranges/intervals. Upon the S3 class range, one could define confidence/prediction intervals in a compact way, i.e. one column instead of three (including lower, upper and level). It provides the back-end for tbl_forecast in the tsibble package.

Installation

You could install the development version from Github using

# install.packages("devtools")
devtools::install_github("earowang/hilo")

How it works

library(hilo)
x <- rnorm(15)
y <- x + rnorm(15)
newdat <- data.frame(x = seq(-3, 3, length.out = 10))
pred <- as.data.frame(predict(lm(y ~ x), newdat, interval = "prediction"))
pred$PI <- bind_rng(lower = pred$lwr, upper = pred$upr, level = 95L)
pred
#>     fit   lwr   upr               PI
#> 1  -4.2 -6.76 -1.54 [-6.76, -1.54]95
#> 2  -3.2 -5.67 -0.80 [-5.67, -0.80]95
#> 3  -2.3 -4.61 -0.02 [-4.61, -0.02]95
#> 4  -1.4 -3.59  0.81 [-3.59,  0.81]95
#> 5  -0.5 -2.62  1.67 [-2.62,  1.67]95
#> 6   0.4 -1.70  2.59 [-1.70,  2.59]95
#> 7   1.4 -0.83  3.56 [-0.83,  3.56]95
#> 8   2.3 -0.01  4.58 [-0.01,  4.58]95
#> 9   3.2  0.77  5.64 [ 0.77,  5.64]95
#> 10  4.1  1.52  6.73 [ 1.52,  6.73]95


earowang/hilo documentation built on May 18, 2019, 8:07 p.m.