a "formula" describing the linear model to be fit (as
in fxlm.
data
a "zoo" time series.
...
further arguments passed to gbreakpoints (currently unexported,
see below), most of the arguments are identical to the formula method of
breakpoints
hpc
a character specifying the high performance computing support.
Default is "none", can be set to "foreach".
Details
fxregimes segments an exchange rate regression (Frankel-Wei regression)
into different regimes. The breakpoints are chosen to maximize the likelihood of
a Gaussian regression (with regime-specific variances). The number of breakpoints
are selected according to information criteria (by default LWZ, but BIC is also
reported).
The computing engine behind fxregime is gbreakpoints that generalizes
various aspects about breakpoints. Its interface
is not yet fixed, hence it is not exported in the namespace (and not documented).
Most arguments are similar to those of the formula method of breakpoints,
in particular the minimal segment size h and the maximal number of breaks
breaks. To select the default information criterion the new argument
ic can be set either to "LWZ" (the default) or "BIC".
A set of methods for useful generic functions is available, including plot,
print, summary, lines, coef, fitted, residuals,
breakfactor, breakpoints, breakdates, etc. Mostly, they behave
like their "breakpoints" counterparts. Querying information about the
models on each segment is made particularly easy by providing a refit
method that returns a list of fxlm objects.
Optional support for high performance computing is available, currently using
foreach for the dynamic programming algorithm.
If hpc = "foreach" is to be used, a parallel backend should be registered
before. See foreach for more information.
Value
An object of class "fxregimes" inheriting from "gbreakpointsfull",
"gbreakpoints", "breakpointsfull", "breakpoints".
References
Zeileis A., Kleiber C., Krämer W., Hornik K. (2003), Testing and Dating of
Structural Changes in Practice, Computational Statistics and Data Analysis,
44, 109-123.
Shah A., Zeileis A., Patnaik I. (2005), What is the New Chinese
Currency Regime?, Report 23, Department of Statistics and Mathematics,
Wirtschaftsuniversitaet Wien, Research Report Series, November 2005.
http://epub.wu.ac.at.
Zeileis A., Shah A., Patnaik I. (2010), Testing, Monitoring, and Dating Structural
Changes in Exchange Rate Regimes, Computational Statistics and Data Analysis,
54(6), 1696–1706. http://dx.doi.org/10.1016/j.csda.2009.12.005.
See Also
fxlm, fxregimes,
refit
Examples
## load package and data
library("fxregime")
data("FXRatesCHF", package = "fxregime")
## compute returns for CNY (and explanatory currencies)
## for one year after abolishing fixed USD regime
cny <- fxreturns("CNY", frequency = "daily",
start = as.Date("2005-07-25"), end = as.Date("2006-07-24"),
other = c("USD", "JPY", "EUR", "GBP"))
## compute all segmented regression with minimal segment size of
## h = 20 and maximal number of breaks = 5.
reg <- fxregimes(CNY ~ USD + JPY + EUR + GBP,
data = cny, h = 20, breaks = 5, ic = "BIC")
summary(reg)
## minimum BIC is attained for 2-segment (1-break) model
plot(reg)
## two regimes
## 1: tight USD peg
## 2: slightly more relaxed USD peg
round(coef(reg), digits = 3)
sqrt(coef(reg)[, "(Variance)"])
## inspect two individual models by re-fitting
refit(reg)