TimeSeriesAggregate

TimeSeriesAggregate[tseries,dt]

computes the mean value of tseries over non-overlapping windows of width dt.

TimeSeriesAggregate[tseries,dt,f]

applies the function f to the values of tseries in non-overlapping windows of width dt.

Details

  • TimeSeriesAggregate is often used in time series analysis to compute aggregated statistics like yearly averages or monthly totals.
  • TimeSeriesAggregate breaks the time series tseries into disjoint left-closed and right-open windows of equal width dt and applies a function f to the values in each segment.
  • If there are no values in a segment, the segment is ignored.
  • The time series tseries can be a list of values {x1,x2,…}, a list of time-value pairs {{t1,x1},{t2,x2},…}, a TimeSeries, EventSeries, or TemporalData.
  • The window width dt can be given as a positive number, a Quantity, or as a date increment.
  • The window specification {dt,align} can be used to determine the alignment of new times within each window.
  • Settings for window alignment align include Left, Center (default), and Right.
  • TimeSeriesAggregate threads pathwise for multipath TemporalData.

Examples

open allclose all

Basic Examples  (3)

Average successive pairs of values:

In[1]:=
Click for copyable input
Out[1]=

Compute the quarterly standard deviation for a financial time series:

In[1]:=
Click for copyable input
In[2]:=
Click for copyable input
In[3]:=
Click for copyable input
Out[3]=

Aggregate multiple paths simultaneously:

In[1]:=
Click for copyable input

Average over blocks of width 0.15:

In[2]:=
Click for copyable input
In[3]:=
Click for copyable input
Out[3]=

Scope  (20)

Applications  (2)

Properties & Relations  (1)

See Also

MovingMap  TimeSeriesResample  TimeSeriesThread  RegularlySampledQ  MinimumTimeIncrement  TimeSeriesShift  TimeSeriesRescale  TimeSeriesMap  TimeSeriesMapThread  TimeSeriesInsert  TimeSeriesWindow  TimeSeriesModelFit  TemporalData  TimeSeries  EventSeries

Introduced in 2014
(10.0)
| Updated in 2017
(11.1)