qat_analyse_histogram_test_1d: Perform a histogram test with a given metric

Description Usage Arguments Details Value Author(s) References See Also Examples

View source: R/qat_analyse_histogram_test_1d.R

Description

This check divides the data into blocks, estimates their probability density functions by histograms and compares them by using a given metric.

Usage

1
2
3
qat_analyse_histogram_test_1d(measurement_vector, 
co_measurement_vector=measurement_vector, metric="EMD", blocksize=100, numofbars=65, 
factorofbar=100)

Arguments

measurement_vector

The measurement vector, which should be tested.

co_measurement_vector

An optional second measurement vector, which is compared to the first. The default is the first measurement vector.

metric

Metric of the comparison. Details see below.

blocksize

Number of elements, which should be used for each block.

numofbars

Number of bins of the histogram.

factorofbar

Correction factor for non-value bins.

Details

The field will be divided into blocks, with a length given by the parameter blocksize. From these blocks histograms are computed and afterwards compared. As a metric for the comparison one of the following five options are usable: EMD: Earth Mover's Distance (default); KLD: Kullback-Leibler Distance; JSD: Jenson-Shannon Distance; RMS: Root Mean Square; MS: Mean Square. As a result a field is generated, which includes the results of the comparison between every combination of blocks.

Value

It returns a list with the following entries:

field

Result matrix of the comparison.

blocksize

Size of blocks in the first dimension.

numofbars

Number of bins of the used histograms.

metric

Used metric in the comparisons.

runs

Number of blocks, which are compared.

Author(s)

Andre Duesterhus

References

Duesterhus, A., Hense, A. (2012) Advanced Information Criterion for Environmental Data Quality Assurance, \_Advances in Science and Research\_, *8*, 99-104.

See Also

qat_analyse_histogram_test_2d

Examples

1
2
3
4
5
vec <- array(rnorm(1000), c(100, 20))
vec[51:100, ] <- vec[51:100, ] + 2
result <- qat_analyse_histogram_test_2d(vec, metric="EMD", blocksize=4, numofbars=65)
qat_plot_histogram_test(result$field, "test_emd_2d", result$blocksize, result$numofbars, 
"emd", result$runs)

qat documentation built on May 30, 2017, 8:27 a.m.