roll_moment: Calculate a _matrix_ of moment values over a rolling...

In algoquant/HighFreq: High Frequency Time Series Management

Calculate a matrix of moment values over a rolling look-back interval attached at the end points of a time series or a matrix.

Description

Calculate a matrix of moment values over a rolling look-back interval attached at the end points of a time series or a matrix.

Usage

roll_moment(
  timeser,
  funame = "calc_mean",
  method = "moment",
  confl = 0.75,
  startp = 0L,
  endd = 0L,
  step = 1L,
  lookb = 1L,
  stub = 0L
)

Arguments

timeser	A time series or a matrix of data.
funame	A character string specifying the moment function (the default is funame = "calc_mean").
method	A character string specifying the type of the model for the moment (the default is method = "moment").
confl	The confidence level for calculating the quantiles of returns (the default is confl = 0.75).
startp	An integer vector of start points (the default is startp = 0).
endd	An integer vector of end points (the default is endd = 0).
step	The number of time periods between the end points (the default is step = 1).
lookb	The number of end points in the look-back interval (the default is lookb = 1).
stub	An integer value equal to the first end point for calculating the end points (the default is stub = 0).

Details

The function roll_moment() calculates a matrix of moment values, over rolling look-back intervals attached at the end points of the time series timeser.

The function roll_moment() performs a loop over the end points, and at each end point it subsets the time series timeser over a look-back interval equal to lookb number of end points.

It passes the subset time series to the function specified by the argument funame, which calculates the statistic. See the functions calc_*() for a description of the different moments. The function name must be one of the following:

• "calc_mean" for the estimator of the mean (location),

• "calc_var" for the estimator of the dispersion (variance),

• "calc_skew" for the estimator of the skewness,

• "calc_kurtosis" for the estimator of the kurtosis.

(The default is the funame = "calc_mean").

If the arguments endd and startp are not given then it first calculates a vector of end points separated by step time periods. It calculates the end points along the rows of timeser using the function calc_endpoints(), with the number of time periods between the end points equal to step time periods.

For example, the rolling variance at 25 day end points, with a 75 day look-back, can be calculated using the parameters step = 25 and lookb = 3.

The function roll_moment() calls the function calc_momptr() to calculate a pointer to a moment function from the function name funame (string). The function pointer is used internally in the C++ code, but the function calc_momptr() is not exported to R.

The function roll_moment() is implemented in RcppArmadillo C++ code, which makes it several times faster than R code.

Value

A matrix with the same number of columns as the input time series timeser, and the number of rows equal to the number of end points.

Examples

## Not run: 
# Define time series of returns using package rutils
retp <- na.omit(rutils::etfenv$returns$VTI)
# Calculate the rolling variance at 25 day end points, with a 75 day look-back
var_rollfun <- HighFreq::roll_moment(retp, fun="calc_var", step=25, lookb=3)
# Calculate the rolling variance using roll_var()
var_roll <- HighFreq::roll_var(retp, step=25, lookb=3)
# Compare the two methods
all.equal(var_rollfun, var_roll, check.attributes=FALSE)
# Define end points and start points
endd <- HighFreq::calc_endpoints(NROW(retp), step=25)
startp <- HighFreq::calc_startpoints(endd, lookb=3)
# Calculate the rolling variance using RcppArmadillo
var_rollfun <- HighFreq::roll_moment(retp, fun="calc_var", startp=startp, endd=endd)
# Calculate the rolling variance using R code
var_roll <- sapply(1:NROW(endd), function(it) {
  var(retp[startp[it]:endd[it]+1, ])
})  # end sapply
var_roll[1] <- 0
# Compare the two methods
all.equal(drop(var_rollfun), var_roll, check.attributes=FALSE)
# Compare the speed of RcppArmadillo with R code
library(microbenchmark)
summary(microbenchmark(
  Rcpp=HighFreq::roll_moment(retp, fun="calc_var", startp=startp, endd=endd),
  Rcode=sapply(1:NROW(endd), function(it) {
    var(retp[startp[it]:endd[it]+1, ])
  }),
  times=10))[, c(1, 4, 5)]  # end microbenchmark summary

## End(Not run)  # end dontrun

algoquant/HighFreq documentation built on June 10, 2025, 3:54 p.m.