R Under development (unstable) (2024-09-01 r87083 ucrt) -- "Unsuffered Consequences"
Copyright (C) 2024 The R Foundation for Statistical Computing
Platform: x86_64-w64-mingw32/x64

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> library("strucchange")
Loading required package: zoo

Attaching package: 'zoo'

The following objects are masked from 'package:base':

    as.Date, as.Date.numeric

Loading required package: sandwich
> 
> ## Nile data
> data("Nile")
> 
> Nile.rcus <- efp(Nile ~ 1, type = "Rec-CUSUM")
> Nile.ocus <- efp(Nile ~ 1, type = "OLS-CUSUM")
> Nile.re <- efp(Nile ~ 1, type = "RE")
> Nile.rmos <- efp(Nile ~ 1, type = "Rec-MOSUM", h = 0.5)
> Nile.omos <- efp(Nile ~ 1, type = "OLS-MOSUM", h = 0.5)
> Nile.me <- efp(Nile ~ 1, type = "ME", h = 0.5)
> sctest(Nile.rcus)

	Recursive CUSUM test

data:  Nile.rcus
S = 2.0669, p-value = 7.487e-08

> sctest(Nile.ocus)

	OLS-based CUSUM test

data:  Nile.ocus
S0 = 2.9518, p-value = 5.409e-08

> sctest(Nile.ocus, alt = TRUE)

	OLS-based CUSUM test with alternative boundaries

data:  Nile.ocus
S0 = 6.5741, p-value = 1e-04

> sctest(Nile.re)

	RE test (recursive estimates test)

data:  Nile.re
RE = 2.9518, p-value = 5.409e-08

> sctest(Nile.re, alt = TRUE)

	RE test (recursive estimates test) with alternative boundaries

data:  Nile.re
RE = 6.5741, p-value = 1e-04

> sctest(Nile.re, fun = "range")

	RE test (recursive estimates test) with range norm

data:  Nile.re
RE = 2.9518, p-value = 1.831e-06

> sctest(Nile.rmos)

	Recursive MOSUM test

data:  Nile.rmos
M = 5.097, p-value = 0.01

> sctest(Nile.omos)

	OLS-based MOSUM test

data:  Nile.omos
M0 = 2.4237, p-value = 0.01

> sctest(Nile.omos, fun = "range")

	OLS-based MOSUM test with range norm

data:  Nile.omos
M0 = 4.3433, p-value = 5.615e-05

> sctest(Nile.me)

	ME test (moving estimates test)

data:  Nile.me
ME = 2.4237, p-value = 0.01

> sctest(Nile.me, fun = "range")

	ME test (moving estimates test) with range norm

data:  Nile.me
ME = 4.3433, p-value = 5.615e-05

> 
> Nile.fs <- Fstats(Nile ~ 1)
> sctest(Nile.fs, type = "supF")

	supF test

data:  Nile.fs
sup.F = 75.93, p-value = 2.22e-16

> sctest(Nile.fs, type = "aveF")

	aveF test

data:  Nile.fs
ave.F = 21.215, p-value < 2.2e-16

> sctest(Nile.fs, type = "expF")

	expF test

data:  Nile.fs
exp.F = 33.759, p-value < 2.2e-16

> breakpoints(Nile.fs)

	 Optimal 2-segment partition: 

Call:
breakpoints.Fstats(obj = Nile.fs)

Breakpoints at observation number:
28 

Corresponding to breakdates:
1898 
> 
> ## Seatbelt data
> data("UKDriverDeaths")
> seatbelt <- log10(UKDriverDeaths)
> seatbelt <- cbind(seatbelt, lag(seatbelt, k = -1), lag(seatbelt, k = -12))
> colnames(seatbelt) <- c("y", "ylag1", "ylag12")
> seatbelt <- window(seatbelt, start = c(1970, 1), end = c(1984,12))
> 
> seat.rcus <- efp(y ~ ylag1 + ylag12, data = seatbelt, type = "Rec-CUSUM")
> seat.ocus <- efp(y ~ ylag1 + ylag12, data = seatbelt, type = "OLS-CUSUM")
> seat.re <- efp(y ~ ylag1 + ylag12, data = seatbelt, type = "RE")
> seat.rmos <- efp(y ~ ylag1 + ylag12, data = seatbelt, type = "Rec-MOSUM", h = 0.5)
> seat.omos <- efp(y ~ ylag1 + ylag12, data = seatbelt, type = "OLS-MOSUM", h = 0.5)
> seat.me <- efp(y ~ ylag1 + ylag12, data = seatbelt, type = "ME", h = 0.5)
> sctest(seat.rcus)

	Recursive CUSUM test

data:  seat.rcus
S = 1.1599, p-value = 0.008572

> sctest(seat.ocus)

	OLS-based CUSUM test

data:  seat.ocus
S0 = 1.4866, p-value = 0.02407

> sctest(seat.ocus, alt = TRUE)

	OLS-based CUSUM test with alternative boundaries

data:  seat.ocus
S0 = 3.4082, p-value = 0.04502

> sctest(seat.re)

	RE test (recursive estimates test)

data:  seat.re
RE = 1.6311, p-value = 0.02904

> sctest(seat.re, alt = TRUE)

	RE test (recursive estimates test) with alternative boundaries

data:  seat.re
RE = 4.7365, p-value = 3e-04

> sctest(seat.re, fun = "range")

	RE test (recursive estimates test) with range norm

data:  seat.re
RE = 1.9303, p-value = 0.04762

> sctest(seat.rmos)

	Recursive MOSUM test

data:  seat.rmos
M = 2.0539, p-value = 0.04259

> sctest(seat.omos)

	OLS-based MOSUM test

data:  seat.omos
M0 = 0.91616, p-value = 0.4004

> sctest(seat.omos, fun = "range")

	OLS-based MOSUM test with range norm

data:  seat.omos
M0 = 1.4949, p-value = 0.5175

> sctest(seat.me)

	ME test (moving estimates test)

data:  seat.me
ME = 1.7107, p-value = 0.04712

> sctest(seat.me, fun = "range")

	ME test (moving estimates test) with range norm

data:  seat.me
ME = 2.1956, p-value = 0.3007

> 
> seat.fs <- Fstats(y ~ ylag1 + ylag12, data = seatbelt, from = 0.1)
> sctest(seat.fs, type = "supF")

	supF test

data:  seat.fs
sup.F = 19.333, p-value = 0.006721

> sctest(seat.fs, type = "aveF")

	aveF test

data:  seat.fs
ave.F = 7.458, p-value = 0.01461

> sctest(seat.fs, type = "expF")

	expF test

data:  seat.fs
exp.F = 6.4247, p-value = 0.008093

> breakpoints(seat.fs)

	 Optimal 2-segment partition: 

Call:
breakpoints.Fstats(obj = seat.fs)

Breakpoints at observation number:
46 

Corresponding to breakdates:
1973(10) 
> 
> ## German M1 data
> data("GermanM1")
> LTW.model <- dm ~ dy2 + dR + dR1 + dp + m1 + y1 + R1 + season
> M1.model <- dm ~ dy2 + dR + dR1 + dp + ecm.res + season
> 
> M1.ocus <- efp(LTW.model, data = GermanM1, type = "OLS-CUSUM")
> M1.re <- efp(LTW.model, data = GermanM1, type = "RE")
> M1.fs <- Fstats(LTW.model, data = GermanM1, from = 0.1)
> sctest(M1.ocus)

	OLS-based CUSUM test

data:  M1.ocus
S0 = 0.50881, p-value = 0.958

> sctest(M1.ocus, alt = TRUE)

	OLS-based CUSUM test with alternative boundaries

data:  M1.ocus
S0 = 1.6288, p-value = 0.9704

> sctest(M1.re)

	RE test (recursive estimates test)

data:  M1.re
RE = 1.9821, p-value = 0.008475

> sctest(M1.re, fun = "range")

	RE test (recursive estimates test) with range norm

data:  M1.re
RE = 2.2386, p-value = 0.01844

> sctest(M1.re, alt = TRUE)

	RE test (recursive estimates test) with alternative boundaries

data:  M1.re
RE = 5.4937, p-value = 0.001099

> sctest(M1.fs, type = "supF")

	supF test

data:  M1.fs
sup.F = 108.83, p-value = 4.441e-16

> sctest(M1.fs, type = "aveF")

	aveF test

data:  M1.fs
ave.F = 35.551, p-value = 2.007e-07

> sctest(M1.fs, type = "expF")

	expF test

data:  M1.fs
exp.F = 49.74, p-value < 2.2e-16

> 
> M1 <- historyM1
> ols.efp <- efp(M1.model, type = "OLS-CUSUM", data = M1)
> newborder <- function(k) 1.5778*k/118
> ols.mefp <- mefp(ols.efp, period = 2)
> ols.mefp2 <- mefp(ols.efp, border = newborder)
> M1 <- GermanM1
> ols.mon <- monitor(ols.mefp)
Break detected at observation # 128 
> ols.mon2 <- monitor(ols.mefp2)
Break detected at observation # 135 
> ols.mon
Monitoring with OLS-based CUSUM test 

Initial call:
  mefp.efp(obj = ols.efp, period = 2) 

Last call:
  monitor(obj = ols.mefp) 

Significance level   :  0.05 
Critical value       :  2.795483 
History size         :  118 
Last point evaluated :  140 
Structural break at  :  128 

Parameter estimate on history :
(Intercept)         dy2          dR         dR1          dp     ecm.res 
-0.05025441 -0.29729418 -0.67278600 -0.99950033 -0.52786586  1.00000000 
   seasonQ1    seasonQ2    seasonQ3 
-0.13330148 -0.01559447 -0.10906796 
> ols.mon2
Monitoring with OLS-based CUSUM test 

Initial call:
  mefp.efp(obj = ols.efp, border = newborder) 

Last call:
  monitor(obj = ols.mefp2) 

Significance level   :  0.05 
Critical value       :  2.795483 
History size         :  118 
Last point evaluated :  140 
Structural break at  :  135 

Parameter estimate on history :
(Intercept)         dy2          dR         dR1          dp     ecm.res 
-0.05025441 -0.29729418 -0.67278600 -0.99950033 -0.52786586  1.00000000 
   seasonQ1    seasonQ2    seasonQ3 
-0.13330148 -0.01559447 -0.10906796 
> 
> ## Grossarl data
> data("Grossarl")
> Grossarl.bp <- breakpoints(fraction ~ 1, data = Grossarl, h = 0.1)
> summary(Grossarl.bp)

	 Optimal (m+1)-segment partition: 

Call:
breakpoints.formula(formula = fraction ~ 1, h = 0.1, data = Grossarl)

Breakpoints at observation number:
                                    
m = 1                127            
m = 2      55        122            
m = 3      55        124         180
m = 4      55        122     157 179
m = 5      54 86     122     157 179
m = 6   35 55 86     122     157 179
m = 7   35 55 80 101 122     157 179
m = 8   35 55 79 99  119 139 159 179

Corresponding to breakdates:
                                               
m = 1                       1826               
m = 2        1754           1821               
m = 3        1754           1823           1879
m = 4        1754           1821      1856 1878
m = 5        1753 1785      1821      1856 1878
m = 6   1734 1754 1785      1821      1856 1878
m = 7   1734 1754 1779 1800 1821      1856 1878
m = 8   1734 1754 1778 1798 1818 1838 1858 1878

Fit:
                                                                         
m   0         1         2         3         4         5         6        
RSS    1.1088    0.8756    0.6854    0.6587    0.6279    0.6019    0.5917
BIC -460.8402 -497.4625 -535.8459 -533.1857 -532.1789 -530.0501 -522.8510
                       
m   7         8        
RSS    0.5934    0.6084
BIC -511.7017 -496.0924
> confint(Grossarl.bp)

	 Confidence intervals for breakpoints
	 of optimal 3-segment partition: 

Call:
confint.breakpointsfull(object = Grossarl.bp)

Breakpoints at observation number:
  2.5 % breakpoints 97.5 %
1    52          55     61
2   116         122    124

Corresponding to breakdates:
  2.5 % breakpoints 97.5 %
1  1751        1754   1760
2  1815        1821   1823
> 
> 
> proc.time()
   user  system elapsed 
   0.84    0.21    1.04