acs {CoSMoS} | R Documentation |
Provides a parametric function that describes the values of the linear autocorrelation up to desired lags. For more details on the parametric autocorrelation structures see section 3.2 in Papalexiou (2018).
acs(id, ...)
id |
autocorrelation structure id |
... |
other arguments (t as lag and acs parameters) |
Papalexiou, S.M. (2018). Unified theory for stochastic modelling of hydroclimatic processes: Preserving marginal distributions, correlation structures, and intermittency. Advances in Water Resources, 115, 234-252, doi: 10.1016/j.advwatres.2018.02.013
library(CoSMoS)
## specify lag
t <- 0:10
## get the ACS
f <- acs('fgn', t = t, H = .75)
b <- acs('burrXII', t = t, scale = 1, shape1 = .6, shape2 = .4)
w <- acs('weibull', t = t, scale = 2, shape = 0.8)
p <- acs('paretoII', t = t, scale = 3, shape = 0.3)
## visualize the ACS
dta <- data.table(t, f, b, w, p)
m.dta <- melt(dta, id.vars = 't')
ggplot(m.dta,
aes(x = t,
y = value,
group = variable,
colour = variable)) +
geom_point(size = 2.5) +
geom_line(lwd = 1) +
scale_color_manual(values = c('steelblue4', 'red4', 'green4', 'darkorange'),
labels = c('FGN', 'Burr XII', 'Weibull', 'Pareto II'),
name = '') +
labs(x = bquote(lag ~ tau),
y = 'Acf') +
scale_x_continuous(breaks = t) +
theme_classic()