Methods for class ‘mmctestres’ and ‘mmctest’, Package ‘simctest’

Description

Function which returns a list containing lower confidence limits (vector ‘lowerLimits’) and upper confidence limits (vector ‘upperLimits’).

Usage

 confidenceLimits(obj)

Arguments

Methods

confidenceLimits(obj)

works with object of type mmctestres or mmctest.

Examples

  fun <- function(ind,n,data) sapply(1:length(ind), function(i) sum(runif(n[i])<=data[ind[i]]));
  i <- mmctSampler(fun,num=500,data=runif(500));
  a <- mmctest(h=hBH);
  a <- run(a, i, maxsteps=list(maxnum=1000000,undecided=10));
  res <- confidenceLimits(a);
  lower <- res$lowerLimits;
  upper <- res$upperLimits;

Methods for Function run in Package ‘simctest’

Description

Computes a confidence interval for the p-value

Usage

confint(object,parm,level=0.95,...)

Arguments

Methods

object = "ANY", parm = "ANY"

Generic function: see confint.

object = "sampalgres", parm = "missing"

Computes a confidence interval for the p-value with the coverage probability given by level.

Examples

alg<-getalgonthefly()
res <- run(alg, function() runif(1)<0.05);
res
confint(res)

Methods for Function ‘cont’ in Package ‘simctest’

Description

Continues the sampling for some more steps.

Usage

 cont(data,steps)

Arguments

Methods

data = "sampalgres"

works with the algorithm based on precomputation.

data = "sampalgontheflyres"

works with the on-the-fly algorithm.

data = "mmctestres"

works with object of type "mmctestres".

Examples

res <- simctest(function() runif(1)>0.95,maxsteps=10);
res
res <- cont(res,1000)
res
res <- cont(res,1000)
res

Methods for Function getL in Package ‘simctest’

Description

Returns the lower boundary for the stopping rule

Usage

##S4 method
getL(alg,ind)

Arguments

Methods

alg = "sampalgPrecomp"

the sampling algorithm to be used

Examples

   getL(getalgprecomp(),1:100)

Methods for Function ‘cont’ in class ‘mmctestres’, Package ‘simctest’

Description

Function to request number of hypotheses.

Usage

 getNumber(obj)

Arguments

Methods

getNumber(obj)

works with object of type "mmctSampler" derived from class "mmctSamplerGeneric".

Examples

  fun <- function(ind,n,data) sapply(1:length(ind), function(i) sum(runif(n[i])<=data[ind[i]]));
  i <- mmctSampler(fun,num=500,data=runif(500));
  number <- getNumber(i);

Methods for Function ‘cont’ in class ‘mmctestres’, Package ‘simctest’

Description

Function to request further samples from certain hypotheses.

Usage

 getSamples(obj, ind, n)

Arguments

Methods

getSamples(obj, ind, n)

works with object of type "mmctSampler" derived from class "mmctSamplerGeneric".

Examples

  fun <- function(ind,n,data) sapply(1:length(ind), function(i) sum(runif(n[i])<=data[ind[i]]));
  i <- mmctSampler(fun,num=500,data=runif(500));
  samples <- getSamples(i, c(1,2), c(2,2));

Methods for Function getU in Package ‘simctest’

Description

Returns the upper boundary for the stopping rule

Usage

getU(alg,ind)

Arguments

Methods

alg = "sampalgPrecomp"

the sampling algorithm to be used

Examples

   getU(getalgprecomp(),1:100)

Construct algorithms

Description

Constructs classes of type sampalgonthefly and sampalgPrecomp.

Usage

getalgonthefly(level = 0.05, epsilon = 0.001, halfspend = 1000)
getalgprecomp(level = 0.05, epsilon = 0.001, halfspend = 1000)

Arguments

Value

getalgonthefly returns an object of type sampalgonthefly. getalgprecomp returns an object of type sampalgPrecomp.

Author(s)

Axel Gandy

References

Gandy, A. (2009) Sequential Implementation of Monte Carlo Tests with Uniformly Bounded Resampling Risk. JASA, 104(488):1504-1511.

Examples

alg<-getalgprecomp()
run(alg, function() runif(1)<0.01)

alg<-getalgonthefly()
run(alg, function() runif(1)<0.01)

Methods for Function getbounds in Package ‘simctest’

Description

returns bounds on the p.value if the algorithm has not stopped yet.

Usage

getbounds(data)

Arguments

Method for class ‘mcmtest’, Package ‘simctest’

Description

Implementation of the multiple testing procedure by Benjamini-Hochberg.

Usage

 hBH(p, threshold)

Arguments

Methods

hBH(p, threshold)

applies the Benjamini-Hochberg procedure to p-values p with given threshold, returns rejected indices

Examples

hBH(runif(10),threshold=0.1)

Method for class ‘mcmtest’, Package ‘simctest’

Description

Implementation of independent (Bonferroni) multiple testing.

Usage

 hBonferroni(p, threshold)

Arguments

Methods

hBonferroni(p, threshold)

performs independent multiple testing using the Bonferroni correction at given threshold, returns rejected indices

Examples

hBonferroni(runif(10),threshold=0.1)

Method for class ‘mcmtest’, Package ‘simctest’

Description

Implementation of the multiple testing procedure by Pounds&Cheng.

Usage

 hPC(p, threshold)

Arguments

Methods

hPC(p, threshold)

applies the modification by Pounds&Cheng to p-values p with given threshold, returns rejected indices

Examples

hPC(runif(10),threshold=0.1)

Function mcp in package ‘simctest’

Description

An algorithm for the computation of the power of Monte Carlo tests with guaranteed precision

Usage

mcp(genstream,alpha=0.05,delta="adaptive",
cp=0.99,maxeffort=Inf,options = list())

Arguments

Details

options$maxeffort: set to maximum allowable effort.

options$reports: set to FALSE if onscreen reports are not wanted.

options$file: optional file-name to save results to.

options$pilotn: number of streams in pilot (1000 by default).

options$pilotmaxsteps: maxsteps in pilot (1000 by default).

options$gammapilotprop: proportion of error spent on pilot CI (0.1 by default)

options$gammatestprop: proportion of error spent on testing remaining paths (default is 0.1)

options$spendgammatest: spending sequence for the testing procedure on the remaining streams. Must be a non-negative function of integers with positive limit 1 (t/(20+t) by default).

options$eta: internal parameter to the testing procedure on the remaining streams (0.05 by default).

options$maxstepsbase: initial maximum number of steps (500 by default)

options$maxstepsinc: multiplier for the maximum number of steps thereafter (1.5 by default).

options$maxbatch: multiplier for the maximum number of steps thereafter (200000 by default).

options$deltamid: adaptive delta function. Describes the length of the confidence interval desired depending on the midpoint of the interval. By default the function requires 0.02 for intervals containing 0.05 or lower or 0.95 or higher, and 0.1 otherwise. If using non-default adaptive delta must also specify epsilon (below).

options$epsilon: error probability for each stream. Only set if using non-standard adaptive delta.

Value

An object of class "mcpres" with slots:

Author(s)

Axel Gandy and Patrick Rubin-Delanchy

References

Gandy, A. and Rubin-Delanchy, P. An algorithm to compute the power of Monte Carlo tests with guaranteed precision. Annals of Statistics, 41(1):125–142, 2013.

See Also

mkdeltamid

Examples

#The following example takes a bit of computing time
## Not run: 
#Example where we know the power should be the level of the test
genstream <- function(){p <- runif(1); function(N){runif(N) <= p}}

res <- mcp(genstream, alpha=0.05, delta="adaptive", cp=0.99)

#should find confidence interval of length 0.02 centered around 0.05
res

## End(Not run)

Class "mcpres"

Description

Result returned by mcp

Objects from the Class

Objects can be created by calls of the form new("mcpres", ...).

Slots

int:

Object of class "numeric"

cp:

Object of class "numeric"

beta:

Object of class "numeric"

N:

Object of class "numeric"

effort:

Object of class "numeric"

rescount:

Object of class "numeric"

truncated:

Object of class "logical"

taccepted:

Object of class "logical"

Methods

show

signature(object = "mcpres"): ...

Author(s)

Axel Gandy and Patrick Rubin-Delanchy

References

Gandy, A. and Rubin-Delanchy, P (2013). An Algorithm to compute the power of Monte Carlo tests with guaranteed precision. Annals of Statistics, 41(1):125–142.

Examples

showClass("mcpres")

Sequential implementation of Monte Carlo tests with p-valube buckets

Description

Sequential implementation of the Monte Carlo test with p-value buckets.

Implementation of the Robbins-Lai (mctest.RL) and SIMCTEST (mctest.simctest) approaches to compute a decision interval (and decision) with respect to several thresholds/ p-value buckets. The function "mctest" is a wrapper function for both the Robbins-Lai and the SIMCTEST approach which calls one of the two using an additional parameter "method" (method="simctest" for SIMCTEST and method="RL" for Robbins-Lai).

Usage

mctest(gen,J=Jstar,epsilon=0.001,batch=10,batchincrement=1.1,maxbatch=100,
  method=c("simctest","RL"))
mctest.RL(gen,J=Jstar,epsilon=0.001,batch=10,batchincrement=1.1,maxbatch=100)
mctest.simctest(gen,J=Jstar,epsilon=0.001,batch=10,batchincrement=1.1,maxbatch=100)
J
Jstar
## S3 method for class 'mctestres'
print(x,...)

Arguments

Value

mctest, mctest.RL and mctest.simctest all return an object of class type mctestres, which has a print function (print.mctestres).

An object of class mctestres is a list with the following components: step (total batched number of samples drawn), decision.interval (interval for the p-value), decision (expressing significance), est.p (an estimate of the p-value) and realn (the actual number of samples taken without batching).

References

Ding, D., Gandy, A. and Hahn, G. (2019) Implementing Monte Carlo Tests with P-value Buckets. To appear in Scandinavian Journal of Statistics. arXiv:1703.09305 [stat.ME].

Examples

  #Example used in the above paper
  dat <- matrix(nrow=5,ncol=7,byrow=TRUE,
                c(1,2,2,1,1,0,1, 2,0,0,2,3,0,0, 0,1,1,1,2,7,3, 1,1,2,0,0,0,1, 0,1,1,1,1,0,0))
  loglikrat <- function(data){
    cs <- colSums(data)
    rs <- rowSums(data)
    mu <- outer(rs,cs)/sum(rs)
    2*sum(ifelse(data<=0.5, 0,data*log(data/mu)))
  }
  resample <- function(data){
    cs <- colSums(data)
    rs <- rowSums(data)
    n <- sum(rs)
    mu <- outer(rs,cs)/n/n
    matrix(rmultinom(1,n,c(mu)),nrow=dim(data)[1],ncol=dim(data)[2])
  }
  t <- loglikrat(dat);

  # function to generate samples
  gen <- function(){loglikrat(resample(dat))>=t}

  #using simctest
  mctest(gen)
  mctest.simctest(gen)
  mctest.RL(gen)

Function mkdeltamid in Package ‘simctest’

Description

Easy creation of adaptive delta function

Usage

mkdeltamid(mindelta=0.02, maxdelta=0.1, llim=0.05, rlim=0.95)

Arguments

Value

A function, say deltamid, that specifies the user's desired precision depending on the midpoint of the computed confidence interval. If the current confidence interval has a midpoint M, then the algorithm will stop if deltamid(M) <= length of CI.

Author(s)

Axel Gandy and Patrick Rubin-Delanchy

References

Gandy, A. and Rubin-Delanchy, P (2013). An Algorithm to compute the power of Monte Carlo tests with guaranteed precision. Annals of Statistics, 41(1):125–142.

Examples

## only care about powers around 0.9 or higher
## (e.g. if want to check that the test is powerful enough).

deltamid <- mkdeltamid(mindelta=0.02, maxdelta=1, llim=0, rlim=0.9)

genstream <- function(){p <- runif(1); function(N){runif(N) <= p}}

## The power is 0.05. The algorithm should stop as soon as it is clear
## that the power is not larger than 0.9. (Must specify epsilon
## if using non-standard delta.)

res <- mcp(genstream, alpha=0.05, delta="adaptive", cp=0.99,
options=list(deltamid = deltamid, epsilon = 0.0001))

##should stop early.
res

Class "mmctest"

Description

Wrapper-Class for "mmctestInterfaceGeneric", takes a function, the number of hypotheses and returns derived object of class "mmctestInterfaceGeneric". Class provides a slot for additional data. The function f(ind,n,data) has to return n[i] new samples for each hypothesis ind[i] in vector "ind", where i=1...length(ind). The data stored in the data slot of class "mmctSampler" is also passed on to "f".

Objects from the Class

Objects can be created by calls of the form mmctSampler(f=...,num=...,data=...).

Slots

f:

Object of class "function"

num:

Object of class "numeric"

data:

Object of class "numeric"

Methods

getSamples

signature(obj="mmctSampler", ind="numeric", n="numeric"): ...

getNumber

signature(obj="mmctSampler"): ...

Author(s)

Axel Gandy and Georg Hahn

References

Gandy, A. and Hahn, G. (2014) MMCTest - a safe algorithm for implementing multiple Monte Carlo tests. Scandinavian Journal of Statistics, 41(4):1083–1101

Examples

  fun <- function(ind,n,data) sapply(1:length(ind), function(i) sum(runif(n[i])<=data[ind[i]]));
  i <- mmctSampler(fun,num=500,data=runif(500));

Methods for class mmctSampler', Package ‘simctest’

Description

Constructor for class 'mmctSampler'.

Usage

 mmctSampler(f, num, data=NULL)

Arguments

Methods

mmctSampler(f, num, data)

returns object of type 'mmctSampler' (derived from class 'mmctSamplerGeneric').

Examples

  fun <- function(ind,n,data) sapply(1:length(ind), function(i) sum(runif(n[i])<=data[ind[i]]));
  i <- mmctSampler(fun,num=500,data=runif(500));

Class "mmctSamplerGeneric"

Description

Generic class, has to be implemented as "mmctSampler".

Objects from the Class

This is a virtual class - no objects should be derived from it.

Methods

getSamples

signature(obj = "mmctSamplerGeneric", ind = "numeric", n = "numeric"): ...

getNumber

signature(obj = "mmctSamplerGeneric"): ...

Author(s)

Axel Gandy and Georg Hahn

References

Gandy, A. and Hahn, G. (2014) MMCTest - a safe algorithm for implementing multiple Monte Carlo tests. Scandinavian Journal of Statistics, 41(4):1083–1101

Class "mmctest"

Description

Class which creates an object of type "mmctestres".

Objects from the Class

Objects can be created by calls of the form mmctest(h=...).

Slots

internal:

Object of class "environment"

Methods

run

signature(alg = "mmctest", gensample = "mmctSamplerGeneric", maxsteps = "numeric"): ...

Author(s)

Axel Gandy and Georg Hahn

References

Gandy, A. and Hahn, G. (2014) MMCTest - a safe algorithm for implementing multiple Monte Carlo tests. Scandinavian Journal of Statistics, 41(4):1083–1101

Examples

  fun <- function(ind,n,data) sapply(1:length(ind), function(i) sum(runif(n[i])<=data[ind[i]]));
  i <- mmctSampler(fun,num=500,data=runif(500));
  a <- mmctest(h=hBH);
  a <- run(a, i, maxsteps=list(maxnum=1000000,undecided=10));

Methods for class ‘mmctest’, Package ‘simctest’

Description

Constructor for class ‘mmctest’.

Usage

 mmctest(epsilon=0.01, threshold=0.1, r=10000, h, thompson=F, R=1000)

Arguments

Methods

mmctest(epsilon=0.01, threshold=0.1, r=10000, h)

returns object of type ‘mmctest’.

Examples

  fun <- function(ind,n,data) sapply(1:length(ind), function(i) sum(runif(n[i])<=data[ind[i]]));
  i <- mmctSampler(fun,num=500,data=runif(500));
  a <- mmctest(h=hBH);
  a <- run(a, i, maxsteps=list(maxnum=1000000,undecided=10));

Class "mmctestres"

Description

Class which stores current result of type "mmctest".

Objects from the Class

Objects should not be created directly. Objects returned by calls of the form new("mmctest", ...) are of type mmctestres.

Slots

internal:

Object of class "environment"

epsilon:

Object of class "numeric"

threshold:

Object of class "numeric"

r:

Object of class "numeric"

R:

Object of class "numeric"

h:

Object of class "function"

gensample:

Object of class "mmctSamplerGeneric"

g:

Object of class "numeric"

num:

Object of class "numeric"

A:

Object of class "numeric"

B:

Object of class "numeric"

C:

Object of class "numeric"

thompson:

Object of class "logical"

rejprob:

Object of class "logical"

Methods

mainalg

signature(obj = "mmctestres", stopcrit = "numeric"): ...

cont

signature(data = "mmctestres", steps = "numeric"): ...

show

signature(object = "mmctestres"): ...

pEstimate

signature(obj = "mmctestres"): ...

rejProb

signature(obj = "mmctestres"): ...

confidenceLimits

signature(obj = "mmctestres"): ...

testResult

signature(obj = "mmctestres"): ...

summary.mmctestres

signature(object = "mmctestres"): ...

Author(s)

Axel Gandy and Georg Hahn

References

Gandy, A. and Hahn, G. (2014) MMCTest - a safe algorithm for implementing multiple Monte Carlo tests. Scandinavian Journal of Statistics, 41(4):1083–1101

Examples

  fun <- function(ind,n,data) sapply(1:length(ind), function(i) sum(runif(n[i])<=data[ind[i]]));
  i <- mmctSampler(fun,num=500,data=runif(500));
  a <- mmctest(h=hBH);
  a <- run(a, i, maxsteps=list(maxnum=1000000,undecided=10));
  # a is object of type "mmctestres" now

Methods for class ‘mmctestres’ and ‘mmctest’, Package ‘simctest’

Description

Function which shows current estimates of p-values.

Usage

 pEstimate(obj)

Arguments

Methods

pEstimate(obj)

works with object of type mmctestres or mmctest.

Examples

  fun <- function(ind,n,data) sapply(1:length(ind), function(i) sum(runif(n[i])<=data[ind[i]]));
  i <- mmctSampler(fun,num=500,data=runif(500));
  a <- mmctest(h=hBH);
  a <- run(a, i, maxsteps=list(maxnum=1000000,undecided=10));
  pEstimate(a);

Methods for class ‘mmctestres’ and ‘mmctest’, Package ‘simctest’

Description

Function which returns empirical rejection probabilities. Threshold against e.g. 0.5 to obtain rejections (all rejProb>0.5 are rejected). Important: For usage in connection with thompson=TRUE (see the mmctest constructor).

Usage

 rejProb(obj)

Arguments

Methods

rejProb(obj)

works with object of type mmctestres or mmctest.

Examples

  fun <- function(ind,n,data) sapply(1:length(ind), function(i) sum(runif(n[i])<=data[ind[i]]));
  i <- mmctSampler(fun,num=500,data=runif(500));
  a <- mmctest(h=hBH);
  a <- run(a, i, maxsteps=list(maxnum=1000000,undecided=10));
  rejProb(a);

Methods for Function run in Package ‘simctest’

Description

Starts a sampling algorithm

Usage

  run(alg,gensample,maxsteps)

Arguments

Methods

alg = "sampalgPrecomp"

the algorithm to be used

alg = "sampalgonthefly"

the algorithm to be used

alg = "mmctest", gensample = "mmctSamplerGeneric"

the algorithm to be used

Examples

alg<-getalgonthefly()
res <- run(alg, function() runif(1)<0.2);
res

Class "sampalg"

Description

Virtual base class for several sequential sampling algorithms.

Objects from the Class

This is a virtual class - no objects should be derived from it.

Slots

internal:

Internal status data of the algorithm. Object of class "environment"

Methods

No methods defined with class "sampalg" in the signature.

Author(s)

Axel Gandy

See Also

sampalgonthefly, sampalgPrecomp

Class "sampalgPrecomp"

Description

A sampling algorithm that precomputes the boundaries

Objects from the Class

Objects can be created by calls to getalgprecomp

Slots

internal:

internal state of the object. Do not access.

Extends

Class "sampalg", directly.

Author(s)

Axel Gandy

References

Gandy, A. (2009) Sequential Implementation of Monte Carlo Tests with Uniformly Bounded Resampling Risk. JASA 104(488):1504-1511.

Examples

showClass("sampalgPrecomp")

Class "sampalgonthefly"

Description

A sequential sampling algorithm that creates its boundaries on the fly.

Objects from the Class

Objects can be created by calls of the form getalgonthefly(level,epsilon,halfspend).

Slots

internal:

Object of class "environment". Internal state of the algorithm. Do not access.

Extends

Class "sampalg", directly.

Methods

run

signature(alg = "sampalgonthefly"): ...

getboundaryandprob

signature(alg = "sampalgonthefly"): ...

Author(s)

Axel Gandy

References

Gandy, A. (2009) Sequential Implementation of Monte Carlo Tests with Uniformly Bounded Resampling Risk. JASA 104(488):1504-1511.

See Also

sampalgPrecomp

Examples

showClass("sampalgonthefly")

Class "sampalgontheflyres"

Description

Class returned as result from simctest and run.

Objects from the Class

Objects can be created by calls of the form new("sampalgontheflyres", ...).

Slots

porig:

Object of class "numeric"

U:

Object of class "numeric"

L:

Object of class "numeric"

ind:

Object of class "numeric"

preverr:

Object of class "numeric"

p.value:

Object of class "numeric"

steps:

Object of class "numeric"

pos:

Object of class "numeric"

alg:

Object of class "sampalg"

gen:

Object of class "function"

Extends

Class "sampalgres", directly.

Methods

contalg

signature(data = "sampalgontheflyres"): ...

Author(s)

Axel Gandy

References

Gandy, A. (2009) Sequential Implementation of Monte Carlo Tests with Uniformly Bounded Resampling Risk. JASA 104(488):1504-1511.

See Also

simctest, sampalgres

Examples

showClass("sampalgontheflyres")

Class "sampalgres"

Description

Results returned by run - Internal.

Objects from the Class

Objects can be created by calls of the form new("sampalgres", ...).

Slots

p.value:

Object of class "numeric"

steps:

Object of class "numeric"

pos:

Object of class "numeric"

alg:

Object of class "sampalg"

gen:

Object of class "function"

Methods

confint

signature(object = "sampalgres", parm = "missing"): ...

contalg

signature(data = "sampalgres"): ...

getbounds

signature(data = "sampalgres"): ...

show

signature(object = "sampalgres"): ...

Author(s)

Axel Gandy

References

Gandy, A. (2009) Sequential Implementation of Monte Carlo Tests with Uniformly Bounded Resampling Risk. JASA 104(488):1504-1511.

Examples

showClass("sampalgres")

Sequential implementation of Monte Carlo tests

Description

Wrapper function for convenient use of the sequential implementation of the Monte Carlo test.

Usage

simctest(gensample, level=0.05, epsilon=1e-3, maxsteps=1e4)

Arguments

Value

An object of class sampalgres.

Author(s)

Axel Gandy

References

Gandy, A. (2009) Sequential Implementation of Monte Carlo Tests with Uniformly Bounded Resampling Risk. JASA 104(488):1504-1511.

Examples

  #Example used in the above paper
  dat <- matrix(nrow=5,ncol=7,byrow=TRUE,
                c(1,2,2,1,1,0,1, 2,0,0,2,3,0,0, 0,1,1,1,2,7,3, 1,1,2,0,0,0,1, 0,1,1,1,1,0,0))
  loglikrat <- function(data){
    cs <- colSums(data)
    rs <- rowSums(data)
    mu <- outer(rs,cs)/sum(rs)
    2*sum(ifelse(data<=0.5, 0,data*log(data/mu)))
  }
  resample <- function(data){
    cs <- colSums(data)
    rs <- rowSums(data)
    n <- sum(rs)
    mu <- outer(rs,cs)/n/n
    matrix(rmultinom(1,n,c(mu)),nrow=dim(data)[1],ncol=dim(data)[2])
  }
  t <- loglikrat(dat);

  # function to generate samples
  gen <- function(){loglikrat(resample(dat))>=t}

  #using simctest
  simctest(gen,maxsteps=10000)

  #now trying simctest.cont
  res <- simctest(gen,maxsteps=500)
  res

  cont(res,20000)

Methods for class ‘mmctestres’ and ‘mmctest’, Package ‘simctest’

Description

Function which shows current estimates of p-values.

Usage

  ## S3 method for class 'mmctestres'
summary(object,...)

Arguments

Methods

summary.mmctestres(object)

works with object of type mmctestres or mmctest.

Examples

  fun <- function(ind,n,data) sapply(1:length(ind), function(i) sum(runif(n[i])<=data[ind[i]]));
  i <- mmctSampler(fun,num=500,data=runif(500));
  a <- mmctest(h=hBH);
  a <- run(a, i, maxsteps=list(maxnum=1000000,undecided=10));
  summary.mmctestres(a);

Methods for class ‘mmctestres’ and ‘mmctest’, Package ‘simctest’

Description

Function which returns a list containing indices of rejected hypotheses (vector ‘rejected’), nonrejected hypotheses (vector ‘nonrejected’) and undecided hypotheses (vector ‘undecided’)

Usage

 testResult(obj)

Arguments

Methods

testResult(obj)

works with object of type mmctestres or mmctest.

Examples

  fun <- function(ind,n,data) sapply(1:length(ind), function(i) sum(runif(n[i])<=data[ind[i]]));
  i <- mmctSampler(fun,num=500,data=runif(500));
  a <- mmctest(h=hBH);
  a <- run(a, i, maxsteps=list(maxnum=1000000,undecided=10));
  res <- testResult(a);
  rejected <- res$rejected;
  nonrejected <- res$nonrejected;
  undecided <- res$undecided;