Learn R Programming

highfrequency (version 1.0.1)

Tools for Highfrequency Data Analysis

Description

Provide functionality to manage, clean and match highfrequency trades and quotes data, calculate various liquidity measures, estimate and forecast volatility, detect price jumps and investigate microstructure noise and intraday periodicity. A detailed vignette can be found in the open-access paper "Analyzing Intraday Financial Data in R: The highfrequency Package" by Boudt, Kleen, and Sjoerup (2022, ).

Copy Link

Version

Install

install.packages('highfrequency')

Monthly Downloads

2,554

Version

1.0.1

License

GPL (>= 2)

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/jonathancornelissen/highfrequency

Maintainer

Kris Boudt

Last Published

October 4th, 2023

Functions in highfrequency (1.0.1)

# Check data: #' @keywords internal rdatacheck <- function (rData, multi = FALSE) if ((dim(rData)[2] < 2) & (multi)) stop("Your rData object should have at least 2 columns")

ReMeDIAsymptoticVariance

Asymptotic variance of ReMeDI estimator

DEPRECATED DEPRECATED USE rRVar

exchangeHoursOnly

Extract data from an xts object for the exchange hours only

getAlphaVantageData

Get high frequency data from Alpha Vantage

Aggregate a time series

aggregateQuotes

Aggregate a data.table or xts object containing quote data

businessTimeAggregation

Business time aggregation

Make TAQ format

autoSelectExchangeTrades

Retain only data from the stock exchange with the highest trading volume

aggregateTrades

Aggregate a data.table or xts object containing trades data´

Inference on drift burst hypothesis

Compute log returns

DEPRECATED use spreadPrices

getLiquidityMeasures

Compute Liquidity Measure

getCriticalValues

Get critical value for the drift burst hypothesis t-statistic

SPY realized measures

#' @keywords internal zgamma <- function (x, y, gamma_power) if (x^2 < y) out <- abs(x)^gamma_power else if (gamma_power == 1) out <- 1.094 * sqrt(y) if (gamma_power == 2) out <- 1.207 * y if (gamma_power == 4/3) out <- 1.129 * y^(2/3) return(out)

autoSelectExchangeQuotes

Retain only data from the stock exchange with the highest volume

Make Open-High-Low-Close-Volume bars

ReMeDI tuning parameter

Lead-Lag estimation

Aggregate a time series but keep first and last observation

# Difference of medians test # See Fried (2012) # Returns TRUE if H0 is rejected # importFrom stats density # keywords internal DMtest <- function(x, y, alpha = 0.005) m <- length(x) n <- length(y) xmed <- median(x) ymed <- median(y) xcor <- x - xmed ycor <- y - ymed delta1 <- ymed - xmed out <- density(c(xcor, ycor), kernel = "epanechnikov") fmed <- as.numeric(BMS::quantile.density(out, probs = 0.5)) fmedvalue <- (out$y[max(which(out$x < fmed))] + out$y[max(which(out$x < fmed))+1])/2 test <- sqrt((m*n)/(m + n))*2*fmedvalue*delta1 return(abs(test) > qnorm(1-alpha/2))

matchTradesQuotes

Match trade and quote data

Jiang and Oomen (2008) tests for the presence of jumps in the price series.

Returns the positive semidefinite projection of a symmetric matrix using the eigenvalue method

Plotting method for DBH objects

mergeQuotesSameTimestamp

Merge multiple quote entries with the same time stamp

mergeTradesSameTimestamp

Merge multiple transactions with the same time stamp

intradayJumpTest

Intraday jump tests

highfrequency-package

highfrequency: Tools for Highfrequency Data Analysis

getTradeDirection

Get trade direction

plot.HEAVYmodel

Plotting method for HEAVYmodel objects

Cleans quote data

Printing method for DBH objects

Printing method for HARmodel objects

Realized covariances via subsample averaging

to use when p,k different from range [4,6]

predict.HARmodel

Predict method for objects of type HARmodel

listCholCovEstimators

Utility function listing the available estimators for the CholCov estimation

Delete the observations where the bid or ask is zero

listAvailableKernels

Available kernels

Delete the observations where the price is zero

CholCov estimator

Realized covariance

predict.HEAVYmodel

Iterative multi-step-ahead forecasting for HEAVY models

Plot Trade and Quote data

Realized multipower variation

Plotting method for HARmodel objects

Realized bipower covariance

DEPRECATED rMRC

An estimator of integrated quarticity from applying the median operator on blocks of three returns

Modulated realized covariance

An estimator of integrated quarticity from applying the minimum operator on blocks of two returns

Realized outlyingness weighted covariance

Realized quad-power variation of intraday returns

Realized kernel estimator

Robust two time scale covariance estimation

Realized semivariance of highfrequency return series

Realized kurtosis of highfrequency return series.

Realized quarticity

Realized semicovariance

Hayashi-Yoshida covariance

rmTradeOutliersUsingQuotes

Delete transactions with unlikely transaction prices

Threshold Covariance

Sample of cleaned quotes for stock XXX for 2 days measured in microseconds

salesCondition is deprecated. Use tradesCondition instead.

Two time scale covariance estimation

Synchronize (multiple) irregular timeseries by refresh time

rmOutliersTrades

Remove outliers in trades without using quote data

rmOutliersQuotes

Remove outliers in quotes

sampleOneMinuteData

One minute data

Sample of raw quotes for stock XXX for 2 days measured in microseconds

Realized skewness

summary.HARmodel

Summary for HARmodel objects

Convert to format for realized measures

sampleMultiTradeData

Multivariate tick by tick data

Realized tri-power quarticity

An estimator of realized variance.

Cleans trade data

rmNegativeSpread

Delete entries for which the spread is negative

sampleTDataEurope

Sample of cleaned trades for stock XXX for 2 days

Delete entries for which the spread is more than maxi times the median spread

tradesCleanupUsingQuotes

Perform a final cleaning procedure on trade data

Retain only data from a single stock exchange

Sample of raw trades for stock XXX for 2 days

tradesCondition

Delete entries with abnormal trades condition.

Spot Drift Estimation

Spot volatility estimation

Function returns the value, the standard error and the confidence band of the integrated variance (IV) estimator.

Estimators of the integrated variance

HEAVY model estimation

Estimators of the integrated covariance

Internal HEAVY functions

Barndorff-Nielsen and Shephard (2006) tests for the presence of jumps in the price series.

Ait-Sahalia and Jacod (2009) tests for the presence of jumps in the price series.

Heterogeneous autoregressive (HAR) model for realized volatility model estimation