stepbound: Jump estimation under restrictions

Description

Computes piecewise constant maximum likelihood estimators with minimal number of jumps under given restrictions on subintervals.

Deprecation warning: This function is a help function for smuceR and jsmurf and may be removed when these function will be removed.

Usage

stepbound(y, bounds, …)
# S3 method for default
stepbound(y, bounds, x = 1:length(y), x0 = 2 * x[1] - x[2],
  max.cand = NULL, family = c("gauss", "gaussvar", "poisson", "binomial", "gaussKern"),
  param = NULL, weights = rep(1, length(y)), refit = y,
  jumpint = confband, confband = FALSE, …)
# S3 method for stepcand
stepbound(y, bounds, refit = TRUE, …)

Arguments

a vector of numerical observations

bounds

bounds on the value allowed on intervals; typically computed with bounds

a numeric vector of the same length as y containing the corresponding sample points

a single numeric giving the last unobserved sample point directly before sampling started

max.cand, weights

see stepcand

family, param

specifies distribution of data, see family

refit

logical, for family = "gaussKern"; determines whether a fit taken the filter kernel into account will be computed at the end

jumpint

logical (FALSE by default), indicates if confidence sets for jumps should be computed

confband

logical, indicates if a confidence band for the piecewise-continuous function should be computed

…

arguments to be passed to generic methods

Value

An object of class stepfit that contains the fit; if jumpint == TRUE function jumpint allows to extract the confidence interval for the jumps, if confband == TRUE function confband allows to extract the confidence band.

References

Frick, K., Munk, A., and Sieling, H. (2014) Multiscale change-point inference. With discussion and rejoinder by the authors. Journal of the Royal Statistical Society, Series B 76(3), 495--580.

Hotz, T., Sch<U+00FC>tte, O., Sieling, H., Polupanow, T., Diederichsen, U., Steinem, C., and Munk, A. (2013) Idealizing ion channel recordings by a jump segmentation multiresolution filter. IEEE Transactions on NanoBioscience 12(4), 376--386.

Examples

Run this code

# NOT RUN {
# simulate poisson data with two levels
y <- rpois(100, c(rep(1, 50), rep(4, 50)))
# compute bounds
b <- bounds(y, penalty="len", family="poisson", q=4)
# fit step function to bounds
sb <- stepbound(y, b, family="poisson", confband=TRUE)
plot(y)
lines(sb)
# plot confidence intervals for jumps on axis
points(jumpint(sb), col="blue")
# confidence band
lines(confband(sb), lty=2, col="blue")
# }

Run the code above in your browser using DataLab

Data engineering and BI courses are free!