computeTestKolmogorovTruncatedNormal {rotRPackage} | R Documentation |
This ROT function, called from a Test C++ object, is given a sample, a point, the necessary distribution parameters and optionnaly a test level. It then returns the result of a K-S test against the null hypothesis that the sample has un underlying TruncatedNormal distribution of the given parameters and returns a list containing the result and test p-value.
computeTestKolmogorovTruncatedNormal(numericalSample, mu, sigma, a, b, testLevel = 0.95, estimatedParameters)
numericalSample |
the sample to be tested (numeric vector) |
mu |
The TruncatedNormal distribution mu. |
sigma |
The TruncatedNormal distribution sigma. |
a |
The TruncatedNormal distribution aParameter. |
b |
The TruncatedNormal distribution bParameter. |
testLevel |
the test level. (scalar in [0:1]) |
estimatedParameters |
the test level. (scalar in [0:1]) |
A list is returned, containing :
testResult |
The result. 1 means H0 is not rejected. (scalar) |
threshold |
The threshold applied to the p-value when deciding the outcome of the test. |
pValue |
The test p-value. (scalar) |
Pierre-Matthieu Pair, Softia for EDF.
# Standard TruncatedNormal distribution example. (a=0, b=1) sample <- rnorm(1000, 2, 4) sample <- sample[sample > -4 && sample < 6] print(computeTestKolmogorovTruncatedNormal(sample, 2, 4, -4, 6)) print(computeTestKolmogorovTruncatedNormal(sample, 1.5, 4, -4, 6))