PINstimation (version 0.1.2)

vpin: Estimation of Volume-Synchronized PIN model

Description

Estimates the Volume-Synchronized Probability of Informed Trading as developed in Easley2011;textualPINstimation and Easley2012;textualPINstimation.

Usage

vpin(data, timebarsize = 60, buckets = 50, samplength = 50,
            tradinghours = 24, verbose = TRUE)

Value

Returns an object of class estimate.vpin.

Arguments

data

A dataframe with 3 variables: {timestamp, price, volume}.

timebarsize

An integer referring to the size of timebars in seconds. The default value is 60.

buckets

An integer referring to the number of buckets in a daily average volume. The default value is 50.

samplength

An integer referring to the sample length or the window size used to calculate the VPIN vector. The default value is 50.

tradinghours

An integer referring to the length of daily trading sessions in hours. The default value is 24.

verbose

A binary variable that determines whether detailed information about the steps of the estimation of the VPIN model is displayed. No output is produced when verbose is set to FALSE. The default value is TRUE.

Details

The dataframe data should contain at least three variables. Only the first three variables will be considered and in the following order {timestamp, price, volume}.

The property @bucketdata is created as in abad2012;textualPINstimation.

The argument timebarsize is in seconds enabling the user to implement shorter than 1 minute intervals. The default value is set to 1 minute (60 seconds) following Easley et al. (2011, 2012).

The parameter tradinghours is used to eventually correct the duration per bucket. The duration of a given bucket is the difference between the timestamp of the last trade endtime and the timestamp of the first trade stime in the bucket. If the first trade and the last trade in a bucket occur in two different days, and the market trading session does not cover a full day (24 hours); then the duration of the bucket will be inflated. Assume that the daily trading session is 8 hours (tradinghours=8), the start time of a bucket is 2018-10-12 17:06:40 and its end time is 2018-10-13 09:36:00. A straightforward calculation gives that the duration of this bucket is 59,360 secs. However, this duration includes the time during which the market is closed (16 hours). The corrected duration takes into consideration only the time of market activity: duration=59,360-16*3600= 1760 secs, i.e., about 30 minutes.

References

Examples

# There is a preloaded dataset called 'hfdata' contained in the package.
# It is an artificially created high-frequency trading data. The dataset
# contains 100 000 trades and five variables 'timestamp', 'price',
# 'volume', 'bid' and 'ask'. For more information, type ?hfdata.

xdata <- hfdata

# Estimate VPIN model, using the following parameter set where the time
# bar size is 5 minutes, i.e., 300 seconds (timebarsize = 300), 50
# buckets per average daily volume (buckets = 50), and a window size of
# 250 for the VPIN calculation (samplength = 250).

estimate <- vpin(xdata, timebarsize = 300, buckets = 50, samplength = 250)

# Display a description of the estimate

show(estimate)

# Plot the estimated VPIN vector

plot(estimate@vpin, type = "l", xlab = "time", ylab = "VPIN", col = "blue")

# Display the parameters of VPIN estimates

show(estimate@parameters)

# Store the computed data of the different buckets in a dataframe 'buckets'.
# Display the first 10 rows of the dataframe 'buckets'.

buckets <- estimate@bucketdata
show(head(buckets, 10))

# Store the daily VPIN values (weighted and unweighted) in a dataframe
# 'dayvpin'.

# Display the first 10 rows of the dataframe 'dayvpin'.

dayvpin <- estimate@dailyvpin
show(head(dayvpin, 10))