a numerical value meaningful only in the "EL" method. It specifies the number of bootstrap resamples in the Empirical Likelihood method. The default value is 499.
c_sampling
a numerical value meaningful only in the "EL" method. It specifies the constant needed for resampling in the Empirical Likelihood method. The default value is 0.25.
c_F
a numerical value meaningful only in the "EL" method. It specifies the constant needed for estimating the distribution in the Empirical Likelihood method. The default value is 0.25.
c_ELq
a numerical value meaningful only in the "EL" method. It specifies the constant needed for estimating the empirical likelihood function in the Empirical Likelihood method. The default value is 0.25.
c_R
a numerical value meaningful only in the "EL" method. It specifies the constant needed for estimating the ROC Curve in the Empirical Likelihood method. The default value is 0.25.
I
a numerical value meaningful only in the "GPQ" method. It specifies the number of replicates in the Generalized Pivotal Quantity method. The default value is 2500.
Details
The value yielded by this function is used as the control argument of the gsym.point()function.
Author(s)
M<c3><b3>nica L<c3><b3>pez-Rat<c3><b3>n, Carmen Cadarso-Su<c3><a1>rez, Elisa M. Molanes-L<c3><b3>pez and Emilio Let<c3><b3>n
See Also
gsym.point
Examples
library(GsymPoint)
data(melanoma)
###########################################################
# Generalized Pivotal Quantity Method ("GPQ"):
###########################################################
# Change the number of replicates:
gsym.point.GPQ.melanoma<-gsym.point(methods = "GPQ", data = melanoma,
marker = "X", status = "group", tag.healthy = 0, categorical.cov = NULL,
CFN = 1, CFP = 1, control = control.gsym.point(I = 2000),
confidence.level = 0.95, trace = FALSE, seed = FALSE, value.seed = 3)
summary(gsym.point.GPQ.melanoma)
data(prostate)
###########################################################
# Empirical Likelihood Method ("EL")
###########################################################
# Change the number of bootstrap resamples:
gsym.point.EL.prostate <- gsym.point (methods = "EL", data = prostate,
marker = "marker", status = "status", tag.healthy = 0, categorical.cov = NULL,
CFN = 1, CFP = 1, control = control.gsym.point(B=99), confidence.level = 0.95,
trace = FALSE, seed = FALSE, value.seed = 3)
summary(gsym.point.EL.prostate)
Results
R version 3.3.1 (2016-06-21) -- "Bug in Your Hair"
Copyright (C) 2016 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.
R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.
Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.
> library(GsymPoint)
Loading required package: truncnorm
Loading required package: Rsolnp
> png(filename="/home/ddbj/snapshot/RGM3/R_CC/result/GsymPoint/control.gsym.point.Rd_%03d_medium.png", width=480, height=480)
> ### Name: control.gsym.point
> ### Title: Controlling the Generalized Symmetry point computing process
> ### Aliases: control.gsym.point
>
> ### ** Examples
>
> library(GsymPoint)
>
> data(melanoma)
>
> ###########################################################
> # Generalized Pivotal Quantity Method ("GPQ"):
> ###########################################################
>
> # Change the number of replicates:
>
> gsym.point.GPQ.melanoma<-gsym.point(methods = "GPQ", data = melanoma,
+ marker = "X", status = "group", tag.healthy = 0, categorical.cov = NULL,
+ CFN = 1, CFP = 1, control = control.gsym.point(I = 2000),
+ confidence.level = 0.95, trace = FALSE, seed = FALSE, value.seed = 3)
>
> summary(gsym.point.GPQ.melanoma)
*************************************************
OPTIMAL CUTOFF: GENERALIZED SYMMETRY POINT
*************************************************
Call:
gsym.point(methods = "GPQ", data = melanoma, marker = "X", status = "group",
tag.healthy = 0, categorical.cov = NULL, CFN = 1, CFP = 1,
control = control.gsym.point(I = 2000), confidence.level = 0.95,
trace = FALSE, seed = FALSE, value.seed = 3)
According to the Shapiro-Wilk normality test, the marker can be
considered normally distributed in both groups.
Shapiro-Wilk test p-values
Group 0 Group 1
Original marker 0.4719 0.9084
Area under the ROC curve (AUC): 0.906
METHOD: GPQ
Estimate 95% CI lower limit 95% CI upper limit
cutoff -0.8273306 -1.3429871 -0.3542391
Specificity 0.8181698 0.7324915 0.8853894
Sensitivity 0.8181698 0.7324915 0.8853894
>
>
> data(prostate)
>
> ###########################################################
> # Empirical Likelihood Method ("EL")
> ###########################################################
>
> # Change the number of bootstrap resamples:
>
> gsym.point.EL.prostate <- gsym.point (methods = "EL", data = prostate,
+ marker = "marker", status = "status", tag.healthy = 0, categorical.cov = NULL,
+ CFN = 1, CFP = 1, control = control.gsym.point(B=99), confidence.level = 0.95,
+ trace = FALSE, seed = FALSE, value.seed = 3)
According to the Shapiro-Wilk normality test, the marker can not
be considered normally distributed in both groups.
However, after transforming the marker using the Box-Cox
transformation estimate, the Shapiro-Wilk normality test
indicates that the transformed marker can be considered
normally distributed in both groups.
Therefore the GPQ method would be more suitable for this dataset.
Box-Cox lambda estimate = -1.2494
Shapiro-Wilk test p-values
Group 0 Group 1
Original marker 0.0000 0.0232
Box-Cox transformed marker 0.3641 0.2118
>
> summary(gsym.point.EL.prostate)
*************************************************
OPTIMAL CUTOFF: GENERALIZED SYMMETRY POINT
*************************************************
Call:
gsym.point(methods = "EL", data = prostate, marker = "marker",
status = "status", tag.healthy = 0, categorical.cov = NULL,
CFN = 1, CFP = 1, control = control.gsym.point(B = 99), confidence.level = 0.95,
trace = FALSE, seed = FALSE, value.seed = 3)
According to the Shapiro-Wilk normality test, the marker can not
be considered normally distributed in both groups.
However, after transforming the marker using the Box-Cox
transformation estimate, the Shapiro-Wilk normality test
indicates that the transformed marker can be considered
normally distributed in both groups.
Therefore the GPQ method would be more suitable for this dataset.
Box-Cox lambda estimate = -1.2494
Shapiro-Wilk test p-values
Group 0 Group 1
Original marker 0.0000 0.0232
Box-Cox transformed marker 0.3641 0.2118
Area under the ROC curve (AUC): 0.725
METHOD: EL
Estimate 95% CI lower limit 95% CI upper limit
cutoff 67.1199201 58.5560314 74.7152000
Specificity 0.7170686 0.5534702 0.7998167
Sensitivity 0.7170686 0.5534702 0.7998167
>
>
>
>
>
> dev.off()
null device
1
>