A geom to fit a LM model to a short time series

A geom to fit a LM model to a short time series

geom_lm(
  mapping = NULL,
  data = NULL,
  stat = "LM",
  position = "identity",
  show.legend = NA,
  na.rm = FALSE,
  inherit.aes = TRUE,
  warn = TRUE,
  n = 10,
  nBootSamples = 499,
  pValThreshold = 0.05,
  ...
)

Arguments

mapping

Set of aesthetic mappings created by aes(). By default inherit.aes = TRUE, which assigns the top-level plotting aes() to the GLS geom.

data

Input series to be analyzed. If NULL, data is inherited from previous layer or ggplot call.

...

Other arguments may be passed to the stat, including fixed aesthetics.

Value

If slope is significantly different from 0 (p < 0.05), then a line of best fit is returned. Otherwise output is NULL.

Examples

library(ggplot2)

#Generate series

m <- 0.1
x <- 1:10
y <-  m*x + rnorm(10, sd = 0.35)

data <- data.frame(x = x,
                  y = y)

#Plot series with trend
ggplot(data = data) +
  geom_line(aes(x = x, y = y)) +
  geom_lm(aes(x = x, y = y))
#> Error in loadNamespace(x) : there is no package called ‘arfit’
#> Warning: Computation failed in `stat_lm()`.
#> Caused by error in `linear_ar1$pValue`:
#> ! $ operator is invalid for atomic vectors