NAG CL Interface
g13nac (cp_​pelt)

Settings help

CL Name Style:


1 Purpose

g13nac detects change points in a univariate time series, that is, the time points at which some feature of the data, for example the mean, changes. Change points are detected using the PELT (Pruned Exact Linear Time) algorithm using one of a provided set of cost functions.

2 Specification

#include <nag.h>
void  g13nac (Nag_TS_ChangeType ctype, Integer n, const double y[], double beta, Integer minss, const double param[], Integer *ntau, Integer tau[], double sparam[], NagError *fail)
The function may be called by the names: g13nac or nag_tsa_cp_pelt.

3 Description

Let y1:n={yj:j=1,2,,n} denote a series of data and τ={τi:i=1,2,,m} denote a set of m ordered (strictly monotonic increasing) indices known as change points with 1τin and τm=n. For ease of notation we also define τ0=0. The m change points, τ, split the data into m segments, with the ith segment being of length ni and containing yτi-1+1:τi.
Given a cost function, C(yτi-1+1:τi) g13nac solves
minimize m,τ i=1 m (C(yτi-1+1:τi)+β) (1)
where β is a penalty term used to control the number of change points. This minimization is performed using the PELT algorithm of Killick et al. (2012). The PELT algorithm is guaranteed to return the optimal solution to (1) if there exists a constant K such that
C ( y (u+1) : v ) + C ( y (v+1) : w ) + K C ( y (u+1) : w ) (2)
for all u<v<w.
g13nac supplies four families of cost function. Each cost function assumes that the series, y, comes from some distribution, D(Θ). The parameter space, Θ={θ,ϕ} is subdivided into θ containing those parameters allowed to differ in each segment and ϕ those parameters treated as constant across all segments. All four cost functions can then be described in terms of the likelihood function, L and are given by:
C ( y ( τ i-1 +1) : τi ) = -2 log L (θ^i,ϕ| y ( τ i-1 +1) : τi )  
where θ^i is the maximum likelihood estimate of θ within the ith segment. In all four cases setting K=0 satisfies equation (2). Four distributions are available: Normal, Gamma, Exponential and Poisson. Letting
Si= j=τi-1 τi yj  
the log-likelihoods and cost functions for the four distributions, and the available subdivisions of the parameter space are:

4 References

Chen J and Gupta A K (2010) Parametric Statistical Change Point Analysis With Applications to Genetics Medicine and Finance Second Edition Birkhäuser
Killick R, Fearnhead P and Eckely I A (2012) Optimal detection of changepoints with a linear computational cost Journal of the American Statistical Association 107:500 1590–1598

5 Arguments

1: ctype Nag_TS_ChangeType Input
On entry: a flag indicating the assumed distribution of the data and the type of change point being looked for.
ctype=Nag_NormalMean
Data from a Normal distribution, looking for changes in the mean, μ.
ctype=Nag_NormalStd
Data from a Normal distribution, looking for changes in the standard deviation σ.
ctype=Nag_NormalMeanStd
Data from a Normal distribution, looking for changes in the mean, μ and standard deviation σ.
ctype=Nag_GammaScale
Data from a Gamma distribution, looking for changes in the scale parameter b.
ctype=Nag_ExponentialLambda
Data from an exponential distribution, looking for changes in λ.
ctype=Nag_PoissonLambda
Data from a Poisson distribution, looking for changes in λ.
Constraint: ctype=Nag_NormalMean, Nag_NormalStd, Nag_NormalMeanStd, Nag_GammaScale, Nag_ExponentialLambda or Nag_PoissonLambda.
2: n Integer Input
On entry: n, the length of the time series.
Constraint: n2.
3: y[n] const double Input
On entry: y, the time series.
If ctype=Nag_PoissonLambda, that is the data is assumed to come from a Poisson distribution, y+0.5 is used in all calculations.
Constraints:
  • if ctype=Nag_GammaScale, Nag_ExponentialLambda or Nag_PoissonLambda, y[i-1]0, for i=1,2,,n;
  • if ctype=Nag_PoissonLambda, each value of y must be representable as an integer;
  • if ctypeNag_PoissonLambda, each value of y must be small enough such thaty[i-1]2, for i=1,2,,n, can be calculated without incurring overflow.
4: beta double Input
On entry: β, the penalty term.
There are a number of standard ways of setting β, including:
SIC or BIC
β=p×log(n)
AIC
β=2p
Hannan-Quinn
β=2p×log(log(n))
where p is the number of parameters being treated as estimated in each segment. This is usually set to 2 when ctype=Nag_NormalMeanStd and 1 otherwise.
If no penalty is required then set β=0. Generally, the smaller the value of β the larger the number of suggested change points.
5: minss Integer Input
On entry: the minimum distance between two change points, that is τi-τi-1minss.
Constraint: minss2.
6: param[1] const double Input
On entry: ϕ, values for the parameters that will be treated as fixed. If ctype=Nag_GammaScale then param must be supplied, otherwise param may be NULL.
If supplied, then when
ctype=Nag_NormalMean
param[0]=σ, the standard deviation of the normal distribution. If not supplied then σ is estimated from the full input data,
ctype=Nag_NormalStd
param[0]=μ, the mean of the normal distribution. If not supplied then μ is estimated from the full input data,
ctype=Nag_GammaScale
param[0] must hold the shape, a, for the gamma distribution,
otherwise
param is not referenced.
Constraint: if ctype=Nag_NormalMean or Nag_GammaScale, param[0]>0.0.
7: ntau Integer * Output
On exit: m, the number of change points detected.
8: tau[n] Integer Output
On exit: the first m elements of tau hold the location of the change points. The ith segment is defined by y(τi-1+1) to yτi, where τ0=0 and τi=tau[i-1],1im.
The remainder of tau is used as workspace.
9: sparam[2×n+2] double Output
On exit: the estimated values of the distribution parameters in each segment
ctype=Nag_NormalMean, Nag_NormalStd or Nag_NormalMeanStd
sparam[2i-2]=μi and sparam[2i-1]=σi for i=1,2,,m, where μi and σi is the mean and standard deviation, respectively, of the values of y in the ith segment.
It should be noted that σi=σj when ctype=Nag_NormalMean and μi=μj when ctype=Nag_NormalStd, for all i and j.
ctype=Nag_GammaScale
sparam[2i-2]=ai and sparam[2i-1]=bi for i=1,2,,m, where ai and bi are the shape and scale parameters, respectively, for the values of y in the ith segment. It should be noted that ai=param[0] for all i.
ctype=Nag_ExponentialLambda or Nag_PoissonLambda
sparam[i-1]=λi for i=1,2,,m, where λi is the mean of the values of y in the ith segment.
The remainder of sparam is used as workspace.
10: fail NagError * Input/Output
The NAG error argument (see Section 7 in the Introduction to the NAG Library CL Interface).

6 Error Indicators and Warnings

NE_ALLOC_FAIL
Dynamic memory allocation failed.
See Section 3.1.2 in the Introduction to the NAG Library CL Interface for further information.
NE_BAD_PARAM
On entry, argument value had an illegal value.
NE_INT
On entry, minss=value.
Constraint: minss2.
On entry, n=value.
Constraint: n2.
NE_INTERNAL_ERROR
An internal error has occurred in this function. Check the function call and any array sizes. If the call is correct then please contact NAG for assistance.
See Section 7.5 in the Introduction to the NAG Library CL Interface for further information.
NE_NO_LICENCE
Your licence key may have expired or may not have been installed correctly.
See Section 8 in the Introduction to the NAG Library CL Interface for further information.
NE_REAL
On entry, ctype=value and param[0]=value.
Constraint: if ctype=Nag_NormalMean or Nag_GammaScale and param has been supplied, then param[0]>0.0.
NE_REAL_ARRAY
On entry, ctype=value and y[value]=value.
Constraint: if ctype=Nag_GammaScale, Nag_ExponentialLambda or Nag_PoissonLambda then y[i-1]0.0, for i=1,2,,n.
On entry, y[value]=value, is too large.
NW_TRUNCATED
To avoid overflow some truncation occurred when calculating the cost function, C. All output is returned as normal.
To avoid overflow some truncation occurred when calculating the parameter estimates returned in sparam. All output is returned as normal.

7 Accuracy

For efficiency reasons, when calculating the cost functions, C and the parameter estimates returned in sparam, this function makes use of the mathematical identities:
j=u v yj 2 = j=1 v yj 2 - j=1 u-1 yj 2  
and
j=1 n (yj-y¯) 2 = ( j=1 n yj2) - n y¯ 2  
where y¯=n−1j=1nyj.
The input data, y, is scaled in order to try and mitigate some of the known instabilities associated with using these formulations. The results returned by g13nac should be sufficient for the majority of datasets. If a more stable method of calculating C is deemed necessary, g13nbc can be used and the method chosen implemented in the user-supplied cost function.

8 Parallelism and Performance

Background information to multithreading can be found in the Multithreading documentation.
g13nac is not threaded in any implementation.

9 Further Comments

None.

10 Example

This example identifies changes in the mean, under the assumption that the data is normally distributed, for a simulated dataset with 100 observations. A BIC penalty is used, that is β=logn4.6, the minimum segment size is set to 2 and the variance is fixed at 1 across the whole input series.

10.1 Program Text

Program Text (g13nace.c)

10.2 Program Data

Program Data (g13nace.d)

10.3 Program Results

Program Results (g13nace.r)
This example plot shows the original data series, the estimated change points and the estimated mean in each of the identified segments.
GnuplotProduced by GNUPLOT 5.4 patchlevel 6 −3 −2 −1 0 1 2 3 4 0 10 20 30 40 50 60 70 80 90 100 Value Time gnuplot_plot_1 Example Program Simulated time series and the corresponding changes in mean