Fast implementation of meanshift model
fit_meanshift.RdFast implementation of meanshift model
Usage
fit_meanshift(x, tau, distribution = "norm", ...)
fit_meanshift_norm(x, tau, ...)
fit_meanshift_lnorm(x, tau, ...)
fit_meanshift_norm_ar1(x, tau, ...)Arguments
- x
A time series
- tau
a set of indices representing a changepoint set
- distribution
A character indicating the distribution of the data. Should match R distribution function naming conventions (e.g., "norm" for the Normal distribution, etc.)
- ...
arguments passed to
stats::lm()
Value
A mod_cpt object.
Details
fit_meanshift_norm() returns the same model as fit_lmshift() with the
deg_poly argument set to 0.
However, it is faster on large changepoint sets.
fit_meanshift_lnorm() fit the meanshift model with the assumption of
log-normally distributed data.
fit_meanshift_norm_ar1() applies autoregressive errors.
See also
Other model-fitting:
fit_lmshift(),
fit_meanvar(),
fit_nhpp(),
model_args(),
model_name(),
new_fun_cpt(),
whomademe()
Examples
# Manually specify a changepoint set
tau <- c(365, 826)
# Fit the model
mod <- fit_meanshift_norm_ar1(DataCPSim, tau)
# View model parameters
logLik(mod)
#> 'log Lik.' -5195.452 (df=7)
deg_free(mod)
#> [1] 7
# Manually specify a changepoint set
cpts <- c(1700, 1739, 1988)
ids <- time2tau(cpts, as_year(time(CET)))
# Fit the model
mod <- fit_meanshift_norm(CET, tau = ids)
# Review model parameters
glance(mod)
#> # A tibble: 1 × 11
#> pkg version algorithm params num_cpts rmse logLik AIC BIC MBIC MDL
#> <chr> <pckg_> <chr> <list> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 tidych… 0.0.1 meanshif… <dbl> 3 0.575 -313. 642. 673. 672. 683.
# Fit an autoregressive model
mod <- fit_meanshift_norm_ar1(CET, tau = ids)
# Review model parameters
glance(mod)
#> # A tibble: 1 × 11
#> pkg version algorithm params num_cpts rmse logLik AIC BIC MBIC MDL
#> <chr> <pckg_> <chr> <list> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 tidych… 0.0.1 meanshif… <dbl> 3 0.566 -307. 632. 667. 660. 676.