Deborah.Sarah.Jackknife

_make_jackknife_samples(
    data::Vector{T}, 
    bin_size::Integer=1
) -> Vector{T}

Create jackknife samples by leaving out non-overlapping bins of size bin_size.

Arguments

• bin_size: Number of consecutive points to leave out per sample (default = 1).
• data: Original vector of data points.

Returns

• Vector{T} of jackknife sample means.

Notes

• This is Takayuki Sumimoto's legacy. Currently unused.

jackknife_average_error(
    jk::Vector{Float64}
) -> Tuple{Float64, Float64}

Compute the average and jackknife error from jackknife resamples.

Arguments

• jk: Vector of jackknife sample means.

Returns

• (mean, error): Tuple of the overall mean and jackknife standard error.

jackknife_average_error_from_raw(
    arr::AbstractArray, 
    block::Int
) -> Tuple{Float64, Float64}

Compute jackknife average and standard error from raw data

Arguments

• arr: Raw observable array.
• block: Block size for jackknife binning.

Returns

• (mean, stddev)

jackknife_restore_original_single(
    ajk::Vector{Float64}
) -> Vector{Float64}

Reconstruct the original sample values from single-elimination jackknife averages.

Arguments

• ajk: Vector of jackknife sample means (assumed from single-point exclusion).

Returns

• Reconstructed original data values.

Notes

• Currently unused. Benjamin's legacy from his PhD days' experience.

jackknife_standard_error_from_sample_variance(
    jk::Vector{Float64}
) -> Float64

Compute the jackknife estimate of the sample standard deviation.

Arguments

• jk: Vector of jackknife sample means.

Returns

• Jackknife estimate of the standard deviation.

make_jackknife_samples(
    bin_size::Int, 
    data::Vector{T}
) where T -> Vector{T}

Generate jackknife resamples by systematically leaving out bins of data.

Arguments

• bin_size::Int: Size of each jackknife bin.
• data::Vector{T}: Input data vector to resample.

Returns

• data_jk::Vector{T}: Jackknife samples (length = number of bins).