Simultaneous CIs for Ratios of Means of Log-Normal Populations with Zeros

Construct the simultaneous confidence intervals for ratios of means of Log-normal populations with zeros. It also has a Python module that do the same thing, and can be applied to multiple comparisons of parameters of any k mixture distributions. And we provide four methods, the method based on generalized pivotal quantity with order statistics and the quantity based on Wilson by Li et al. (2009) (GPQW), and the methods based on generalized pivotal quantity with order statistics and the quantity based on Hannig (2009) (GPQH). The other two methods are based on two-step MOVER intervals by Amany H, Abdel K (2015) . We deduce Fiducial generalized pivotal two-step MOVER intervals based on Wilson quantity (FMW) and based on Hannig's quantity (FMWH). All these approach you can find in the paper of us which it has been submitted.


Introduction

This R package based on the paper of Simultaneous Confidence Intervals for Ratios of Means of Log-normal Populations with Zeros by Xu et al. It provides 11 methods for construct simultaneous confidence intervals for ratios of means of LN0. At last, we select 4 excellent methods which based on generalized pivotal quantity with order statistics and two-step MOVER intervals. For the convenience of use, we make a R package called LN0SCIs, and it also has a python version package.

Function

We provaide four main functions in our LN0SCIs packages, GPQW,GPQH,FMW and FMWH, if you want to deep understanding these four methods,you can read our paper: Simultaneous Confidence Intervals for Ratios of Means of Log-normal Populations with Zeros. the code we trust in GitHub. If you want to know how to realize them,you can read the source code.

Example

  • GPQW()
library(LN0SCIs)
 
# params setting
p<-c(0.1,0.15,0.1,0.6)
n<-c(30,15,10,50)
mu<-c(1,1.3,2,0)
sigma<-c(1,1,1,2)
C2 <- rbind(c(-1,1,0,0),c(-1,0,1,0),c(-1,0,0,1),c(0,-1,1,0),c(0,-1,0,1),c(0,0,-1,1))
 
N<-1000
GPQW(n,p,mu,sigma,N,C2 = C2) #base function
[1] "====================Method: GPQW===================="
[1] "The Simultaneous Confidence Intervals are:          "
               [LCL,UCL]
1   [-1.235113,2.848869]
2   [-0.441577,7.030192]
3   [-3.57776,-2.108937]
4    [-1.86122,6.480295]
5  [-5.843864,-1.640372]
6 [-10.008059,-2.477454]
[1] "**********************Time**************************"
Time difference of 53.041 secs
  • GPQH
 
p<-c(0.1,0.15,0.1,0.6)
n<-c(30,15,10,50)
mu<-c(1,1.3,2,0)
sigma<-c(1,1,1,2)
C2 <- rbind(c(-1,1,0,0),c(-1,0,1,0),c(-1,0,0,1),c(0,-1,1,0),c(0,-1,0,1),c(0,0,-1,1))
 
N<-1000;
GPQH(n,p,mu,sigma,N,C2 = C2)
[1] "====================Method: GPQH===================="
[1] "The Simultaneous Confidence Intervals are:          "
             [LCL,UCL]
1  [-0.996117,1.07758]
2  [-0.36159,2.378184]
3  [-2.87464,1.273622]
4  [-0.302924,2.22018]
5 [-2.954485,1.098756]
6 [-4.086911,0.345388]
[1] "**********************Time**************************"
Time difference of 16.244 secs
  • FMW
p <- c(0.1,0.15,0.1,0.6)
n <- c(30,15,10,50)
mu <- c(1,1.3,2,0)
sigma <- c(1,1,1,2)
C2 <- rbind(c(-1,1,0,0),c(-1,0,1,0),c(-1,0,0,1),c(0,-1,1,0),c(0,-1,0,1),c(0,0,-1,1))
N <- 1000
 
FMW(n,p,mu,sigma,N,C2 = C2)
[1] "====================Method: FMW===================="
[1] "The Simultaneous Confidence Intervals are:          "
             [LCL,UCL]
1 [-1.351672,0.720717]
2  [-1.11909,2.371603]
3 [-1.882617,2.617392]
4  [-0.86023,2.700871]
5 [-1.618718,2.936072]
6 [-2.967078,2.541986]
[1] "**********************Time**************************"
Time difference of 42.577 secs
  • FMWH
p<-c(0.1,0.15,0.1,0.6)
n<-c(30,15,10,50)
mu<-c(1,1.3,2,0)
sigma<-c(1,1,1,2)
C2 <- rbind(c(-1,1,0,0),c(-1,0,1,0),c(-1,0,0,1),c(0,-1,1,0),c(0,-1,0,1),c(0,0,-1,1))
 
N<-1000;
FMWH(n,p,mu,sigma,N,C2 = C2)
[1] "====================Method: FMWH==================="
[1] "The Simultaneous Confidence Intervals are:          "
             [LCL,UCL]
1 [-1.334835,1.683172]
2 [-0.806956,2.953145]
3 [-2.683212,1.739062]
4 [-1.130242,2.909716]
5 [-2.979693,1.684558]
6 [-4.145004,1.117301]
[1] "**********************Time**************************"
Time difference of 11.152 secs

News

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("LN0SCIs")

0.1.5 by Jing Xu, a year ago


Browse source code at https://github.com/cran/LN0SCIs


Authors: Jing Xu , Xinmin Li , Hua Liang


Documentation:   PDF Manual  


GPL (>= 2) license


Suggests knitr, rmarkdown


See at CRAN