LN_Quant {BayesLN} | R Documentation |
Bayesian estimate of the log-normal quantiles
Description
This function produces an estimate for the log-normal distribution quantile of fixed level quant
.
Usage
LN_Quant(
x,
quant,
method = "weak_inf",
x_transf = TRUE,
guess_s2 = NULL,
CI = TRUE,
alpha_CI = 0.05,
type_CI = "two-sided",
method_CI = "exact",
rel_tol_CI = 1e-05,
nrep_CI = 1e+06
)
Arguments
x |
Vector of data used to estimate the quantile. |
quant |
Number between 0 and 1 that indicates the quantile of interest. |
method |
String that indicates the prior setting to adopt. Choosing |
x_transf |
Logical. If |
guess_s2 |
Specification of a guess for the variance if available. If not, the sample estimate is used. |
CI |
Logical. With the default choice |
alpha_CI |
Level of alpha that determines the credibility (1- |
type_CI |
String that indicates the type of interval to compute: |
method_CI |
String that indicates if the limits should be computed through the logSMNG
quantile function |
rel_tol_CI |
Level of relative tolerance required for the |
nrep_CI |
Number of simulations in case of |
Details
The function allows to carry out Bayesian inference for the unconditional quantiles of a sample that is assumed log-normally distributed.
A generalized inverse Gaussian prior is assumed for the variance in the log scale \sigma^2
, whereas a
flat improper prior is assumed for the mean in the log scale \xi
.
Two alternative hyperparamters setting are implemented (choice controlled by the argument method
): a weakly
informative proposal and an optimal one.
Value
The function returns the prior parameters and their posterior values, summary statistics of the log-scale parameters and the estimate of the specified quantile: the posterior mean and variance are provided by default. Moreover, the user can control the computation of posterior intervals.
Source
Gardini, A., C. Trivisano, and E. Fabrizi. Bayesian inference for quantiles of the log-normal distribution. Biometrical Journal (2020).
Examples
library(BayesLN)
data("EPA09")
# The optimization algorithm might require time:
# LN_Quant(x = EPA09, x_transf = FALSE, quant = 0.95, method = "optimal", CI = FALSE)
LN_Quant(x = EPA09, x_transf = FALSE, quant = 0.95, method = "weak_inf",
alpha_CI = 0.05, type_CI = "UCL", nrep_CI = 1e3) # increase nrep_CI