highfrequency (version 0.7.0.1)

aggregateTS: Aggregate a time series

Description

Function returns aggregated time series as xts object. It can handle irregularly spaced timeseries and returns a regularly spaced one. Use univariate timeseries as input for this function, and check out aggregateTrades and aggregateQuotes to aggregate Trade or Quote data objects.

Usage

aggregateTS(
  ts,
  FUN = "previoustick",
  on = "minutes",
  k = 1,
  weights = NULL,
  dropna = FALSE,
  tz = NULL
)

Arguments

ts

xts object to aggregate.

FUN

function to apply over each interval. By default, previous tick aggregation is done. Alternatively one can set e.g. FUN = "mean". In case weights are supplied, this argument is ignored and a weighted average is taken.

on

character, indicating the time scale in which "k" is expressed. Possible values are: "secs", "seconds", "mins", "minutes", "hours", "days", "weeks", "ticks".

k

positive integer, indicating the number of periods to aggregate over. For example, to aggregate an xts object to the five-minute frequency set k = 5 and on = "minutes".

weights

By default, no weighting scheme is used. When you assign an xts object with wheights to this argument, a weighted mean is taken over each interval. Of course, the weights should have the same timestamps as the supplied time series.

dropna

boolean, which determines whether empty intervals should be dropped. By default, an NA is returned in case an interval is empty, except when the user opts for previous tick aggregation, by setting FUN = "previoustick" (default).

tz

character denoting which timezone the output should be in. Defaults to "GMT"

Value

An xts object containing the aggregated time series.

Details

The timestamps of the new time series are the closing times and/or days of the intervals. E.g. for a weekly aggregation the new timestamp is the last day in that particular week (namely sunday).

In case of previous tick aggregation, for on = "seconds"/"minutes"/"hours", the element of the returned series with e.g. timestamp 09:35:00 contains the last observation up to that point, including the value at 09:35:00 itself.

Please note: In case an interval is empty, by default an NA is returned.. In case e.g. previous tick aggregation it makes sense to fill these NA's by the function na.locf (last observation carried forward) from the zoo package.

In case on = "ticks", the sampling is done such the sampling starts on the first tick, and the last tick is always included For example, if 14 observations are made on one day, and these are 1, 2, 3, ... 14. Then, with on = "ticks" and k = 3, the output will be 1, 4, 7, 10, 13, 14.

Examples

# NOT RUN {
#load sample price data
ts <- sampleTData$PRICE

#Previous tick aggregation to the 5-minute sampling frequency:
tsagg5min <- aggregateTS(ts, on = "minutes", k = 5)
head(tsagg5min)
#Previous tick aggregation to the 30-second sampling frequency:
tsagg30sec <- aggregateTS(ts, on = "seconds", k = 30)
tail(tsagg30sec)

tsagg3ticks <- aggregateTS(ts, on = "ticks", k = 3)

# }