SNSeg_estimate {SNSeg}

Parameter estimates of each segment separated by Self-Normalization (SN) based change-point estimates

Description

The function SNSeg_estimate computes parameter estimates of each segment that are separated by the SN-based change-point estimates.

Usage

SNSeg_estimate(SN_result)

Arguments

SN_result

An S3 object served as the output of the functions SNSeg_Uni, SNSeg_Multi, or SNSeg_HD.

Value

SNSeg_estimate returns an S3 object of class "SNSeg_estimate" including the parameter estimates of each segment separated by the SN-based change-point estimates.

1. If the time series is univariate, for a single parameter change, the output contains parameter estimates for one of the followings: mean, variance, acf, quantile, or general, which can be referred to the change in a single mean, variance, autocorrelation, a given quantile level, or a general functional. For multi-parameter changes, the output can be a combination of mean, variance, acf, and a dataframe with each quantile level depending on the type of parameters (argument paras_to_test of SNSeg_Uni, SNSeg_Multi, or SNSeg_HD) that users select.

2. If the time series is multivariate with a dimension no greater than 10, the output contains parameter estimates for one of the followings: bivcor, multi_mean, or covariance, which can be referred to the change in correlation between bivariate time series and the change in multivariate means or covariance between multivariate time series.

3. If the time series is high-dimensional with a dimension greater than 10, the output contains the parameter estimate HD_mean to represent the change in high-dimensional means.

For more examples of SNSeg_estimate see the help vignette: vignette("SNSeg", package = "SNSeg")

Examples

# code to simulate a univariate time series
set.seed(7)
ts <- MAR_Variance(2, "V1")
ts <- ts[,2]
# test the change in a single parameter (variance)
# grid_size defined
result <- SNSeg_Uni(ts, paras_to_test = "variance", confidence = 0.9,
                    grid_size_scale = 0.05, grid_size = 67,
                    plot_SN = TRUE, est_cp_loc = TRUE)
# estimated change-point locations
result$est_cp
# variance estimates of the separated segments
SNSeg_estimate(SN_result = result)

# For more examples of SNSeg_estimate, please run
# the command: vignette("SNSeg", package = "SNSeg")