Help for package ordinalbayes

Title:

Bayesian Ordinal Regression for High-Dimensional Data

Version:

0.1.2

Date:

2025-04-30

Description:

Provides a function for fitting various penalized Bayesian cumulative link ordinal response models when the number of parameters exceeds the sample size. These models have been described in Zhang and Archer (2021) <doi:10.1186/s12859-021-04432-w>.

License:

MIT + file LICENSE

Depends:

DESeq2, R (≥ 2.10), SummarizedExperiment

Imports:

coda, dclone, runjags

Suggests:

knitr, Biobase, testthat (≥ 3.0.0), rmarkdown

Config/testthat/edition:

Encoding:

UTF-8

LazyData:

true

RoxygenNote:

7.3.2

SystemRequirements:

JAGS (>= 4.0.0)

VignetteBuilder:

knitr

URL:

https://github.com/kelliejarcher/ordinalbayes

BugReports:

https://github.com/kelliejarcher/ordinalbayes/issues

NeedsCompilation:

Packaged:

2025-04-30 16:19:44 UTC; archer.43

Author:

Kellie J. Archer

[aut, cre], Anna Seffernick [ctb], Shuai Sun [ctb], Yiran Zhang [aut]

Maintainer:

Kellie J. Archer <archer.43@osu.edu>

Repository:

CRAN

Date/Publication:

2025-04-30 17:10:02 UTC

Data Frame of Smaller Subset of The Cancer Genome Atlas Cervical Cancer HTSeq Data.

Description

This data.frame is a subset that includes 41 transcripts and four phenotypic variables for 242 subjects with squamous cell cervical cancer.

Usage

cesc

Format

This data.frame includes the following variables:

age_at_index: a numeric vector storing age at cervical cancer diagnosis.
cigarettes_per_day: a numeric vector storing the number of cigarettes smoked per day.
race: a character vector representing race of the subject.
Stage: an ordered factor representing stage of cervical cancer.
ENSG00000076344: a numeric vector representing expression of ENSG00000076344.
ENSG00000077274: a numeric vector representing expression of ENSG00000077274.
ENSG00000101888: a numeric vector representing expression of ENSG00000101888.
ENSG00000115548: a numeric vector representing expression of ENSG00000115548.
ENSG00000122884: a numeric vector representing expression of ENSG00000122884.
ENSG00000125430: a numeric vector representing expression of ENSG00000125430.
ENSG00000131370: a numeric vector representing expression of ENSG00000131370.
ENSG00000135443: a numeric vector representing expression of ENSG00000135443.
ENSG00000136457: a numeric vector representing expression of ENSG00000136457.
ENSG00000138398: a numeric vector representing expression of ENSG00000138398.
ENSG00000150636: a numeric vector representing expression of ENSG00000150636.
ENSG00000161277: a numeric vector representing expression of ENSG00000161277.
ENSG00000163510: a numeric vector representing expression of ENSG00000163510.
ENSG00000164485: a numeric vector representing expression of ENSG00000164485.
ENSG00000164651: a numeric vector representing expression of ENSG00000164651.
ENSG00000166091: a numeric vector representing expression of ENSG00000166091.
ENSG00000166342: a numeric vector representing expression of ENSG00000166342.
ENSG00000171121: a numeric vector representing expression of ENSG00000171121.
ENSG00000177173: a numeric vector representing expression of ENSG00000177173.
ENSG00000180229: a numeric vector representing expression of ENSG00000180229.
ENSG00000188817: a numeric vector representing expression of ENSG00000188817.
ENSG00000197360: a numeric vector representing expression of ENSG00000197360.
ENSG00000203601: a numeric vector representing expression of ENSG00000203601.
ENSG00000225449: a numeric vector representing expression of ENSG00000225449.
ENSG00000230201: a numeric vector representing expression of ENSG00000230201.
ENSG00000233996: a numeric vector representing expression of ENSG00000233996.
ENSG00000236138: a numeric vector representing expression of ENSG00000236138.
ENSG00000236819: a numeric vector representing expression of ENSG00000236819.
ENSG00000250602: a numeric vector representing expression of ENSG00000250602.
ENSG00000253923: a numeric vector representing expression of ENSG00000253923.
ENSG00000256980: a numeric vector representing expression of ENSG00000256980.
ENSG00000259083: a numeric vector representing expression of ENSG00000259083.
ENSG00000259134: a numeric vector representing expression of ENSG00000259134.
ENSG00000260484: a numeric vector representing expression of ENSG00000260484.
ENSG00000263612: a numeric vector representing expression of ENSG00000263612.
ENSG00000264049: a numeric vector representing expression of ENSG00000264049.
ENSG00000264954: a numeric vector representing expression of ENSG00000264954.
ENSG00000265579: a numeric vector representing expression of ENSG00000265579.
ENSG00000271711: a numeric vector representing expression of ENSG00000271711.
ENSG00000272071: a numeric vector representing expression of ENSG00000272071.
ENSG00000276517: a numeric vector representing expression of ENSG00000276517.

Source

TCGAbiolinks TCGA-CESC

Examples

data("cesc")
head(cesc)

Extract Model Coefficients

Description

Extract Model Coefficients

Usage

## S3 method for class 'ordinalbayes'
coef(object, method = mean, ...)

Arguments

object

an ordinalbayes object.

method

The default is method=mean which estimates the mean of each parameter in the MCMC chain. Other options are method=median or any other relevant summary function.

...

other arguements.

Value

alpha

Summary estimates for the thresholds

zeta

Summary estimates for the unpenalized covariates. Only available if unpenalized covariates were included in the fitted model.

beta

Summary estimates for the penalized covariates

gamma

Summary estimates for the variable inclusion indicators. Not available when model="lasso"

Examples


data("cesc")
fit<-ordinalbayes(Stage~1, data=cesc, x=cesc[,5:45],
         model="regressvi", gamma.ind="fixed", pi.fixed=0.99,
         adaptSteps=1000, burnInSteps=1000, nChains=2,
         numSavedSteps=2000, thinSteps=2, seed=26)
coef(fit)

Subset of The Cancer Genome Atlas Cervical Cancer HTSeq Data.

Description

This subset includes 2,009 transcripts and four phenotypic variables for 242 subjects with squamous cell cervical cancer.

Usage

finalSet

Format

The format is of formal class 'DESeqTransform' (package "DESeq2") with the following extractor functions:

assay: includes rld transformed transcript expression data
colData: includes phenotypic data: age_at_index, cigarettes_per_day, race, and Stage

Source

TCGAbiolinks TCGA-CESC

Ordinal Bayesian Regression Models for High-Dimensional Data

Description

Ordinal Bayesian Regression Models for High-Dimensional Data

Usage

ordinalbayes(
  formula,
  data,
  x = NULL,
  subset,
  center = TRUE,
  scale = TRUE,
  a = 0.1,
  b = 0.1,
  model = "regressvi",
  gamma.ind = "fixed",
  pi.fixed = 0.05,
  c.gamma = NULL,
  d.gamma = NULL,
  alpha.var = 10,
  sigma2.0 = NULL,
  sigma2.1 = NULL,
  coerce.var = 10,
  lambda0 = NULL,
  nChains = 3,
  adaptSteps = 5000,
  burnInSteps = 5000,
  numSavedSteps = 9999,
  thinSteps = 3,
  parallel = TRUE,
  seed = NULL,
  quiet = FALSE
)

Arguments

formula

an object of class "formula" (or one that can be coerced to that class): a symbolic description of the model to be fitted. The left side of the formula is the ordinal outcome while the variables on the right side of the formula are the covariates that are not included in the penalization process. Note that if all variables in the model are to be penalized, an intercept only model formula should be specified.

data

an optional data.frame, list or environment (or object coercible by as.data.frame to a data frame) containing the variables in the model.

x

an optional matrix of predictors that are to be penalized in the model fitting process.

subset

an optional vector specifying a subset of observations to be used in the fitting process.

center

logical, if TRUE the penalized predictors are centered.

scale

logical, if TRUE the penalized predictors are scaled.

a

hyperprior for the penalty parameter lambda which is Gamma with parameters a and b.

b

hyperprior for the penalty parameter lambda which is Gamma with parameters a and b.

model

Specify which penalized ordinal model to fit as "regressvi", "lasso", "dess", or "normalss".

gamma.ind

indicates whether prior for the variable inclusion indicators is "fixed" or "random" (for models "regressvi", "dess", or "normalss").

pi.fixed

constant prior for the variable inclusion indicators is when gamma.ind="fixed".

c.gamma

hyperprior for the variable inclusion indicators is when gamma.ind="random".

d.gamma

hyperprior for the variable inclusion indicators is when gamma.ind="random".

alpha.var

variance for alpha_k thresholds in the MCMC chain (default 10).

sigma2.0

variance for the spike when model="normalss" (set to some small positive value).

sigma2.1

variance for the slab when model="normalss" (set to some large positive value).

coerce.var

variance associated with any unpenalized predictors in the MCMC chain (default 10).

lambda0

parameter value for the spike when model="dess".

nChains

number of parallel chains to run (default 3)

adaptSteps

number of iterations for adaptation (default 5,000).

burnInSteps

number of iterations of the Markov chain to run (default 5,000).

numSavedSteps

number of saved steps per chain (default 9,999).

thinSteps

thinning interval for monitors (default 3).

parallel

logical, run the MCMC on multiple processors (default TRUE).

seed

integer, seed to ensure reproducibility.

quiet

logical, when TRUE, suppress output of JAGS (or rjags) when updating models

Value

results An object of class runjags

call Model call

model Name of the ordinal model that was fit

a Value the user specified for a

b Value the user specified for b

featureNames Names of the penalized predictors

center Value the user specified for center

scale Value the user specified for scale

y Observed ordinal response

x Matrix of penalized predictors used in model fitting

w Matrix of unpenalized predictors used in model fitting

gamma.ind Value the user specified for gamma.ind

pi.fixed Value the user specified for pi.fixed if gamma.ind="fixed"

c.gamma Value the user specified for c.gamma if gamma.ind="random"

d.gamma Value the user specified for d.gamma if gamma.ind="random"

sigma2.0 Value the user specified for sigma2.0 if model="normalss"

sigma2.1 Value the user specified for sigma2.1 if model="normalss"

lambda0 value the user specified for lambda0 if model="dess"

Examples


# The number of adaptSteps, burnInSteps, and numSavedSteps was reduced for package testing
data("cesc")
data(reducedSet)
fit<-ordinalbayes(Stage~1, data=cesc, x=cesc[,5:45],
         model="regressvi", gamma.ind="fixed", pi.fixed=0.99,
         adaptSteps=1000, burnInSteps=1000, nChains=2,
         numSavedSteps=2000, thinSteps=2, seed=26)

Trace Plot and/or Density Plot of MCMC Output.

Description

Trace Plot and/or Density Plot of MCMC Output.

Usage

## S3 method for class 'ordinalbayes'
plot(x, trace = TRUE, density = FALSE, ...)

Arguments

x

an ordinalBayes object.

trace

a logical value. If TRUE, trace plots are produced for each variable in the chain.

density

a logical value. If TRUE, density plots are produced for each variable in the chain.

...

other arguments.

Value

No returned value, called for side effects

Examples


data("cesc")
fit<-ordinalbayes(Stage~1, data=cesc, x=cesc[,5:45],
     model="regressvi",gamma.ind="fixed",
     pi.fixed=0.99, adaptSteps=1000, burnInSteps=1000, nChains=2,
     numSavedSteps=2000, thinSteps=2, seed=26)
 plot(fit)

Predicted Probabilities and Class for an Ordinal Bayes Fit.

Description

Predicted Probabilities and Class for an Ordinal Bayes Fit.

Usage

## S3 method for class 'ordinalbayes'
predict(
  object,
  neww = NULL,
  newdata,
  newx = NULL,
  model.select = "average",
  ...
)

Arguments

object

an ordinalBayes fitted object.

neww

an optional formula that includes the unpenalized variables to use for predicting the response. If omitted, the training data are used.

newdata

an optional data.frame that minimally includes the unpenalized variables to use for predicting the response. If omitted, the training data are used.

newx

an optional matrix of penalized variables to use for predicting the response. If omitted, the training data are used.

model.select

when "average" (default) is used, the mean coefficient values over the MCMC chain are used to estimate fitted probabilities; when "median" is used, the median coefficient values over the MCMC chain are used to estimate fitted probabilities; when "max.predicted.class" is used, each step in the chain is used to calculate fitted probabilities and the class. The predicted class is that attaining the maximum fitted probability.

...

other arguments.

Value

predicted

a matrix of predicted probabilities from the fitted model.

class

a vector containing the predicted class taken as that class having the largest predicted probability.

Examples


data("cesc")
fit<-ordinalbayes(Stage~1, data=cesc, x=cesc[,5:45],,
     model="regressvi", gamma.ind="fixed", pi.fixed=0.99,
     adaptSteps=1000, burnInSteps=1000, nChains=2, numSavedSteps=2000,
     thinSteps=2, seed=26)
phat<-predict(fit)
table(phat$class, cesc$Stage)

Print MCMC Summary Statistics

Description

Print MCMC Summary Statistics

Usage

## S3 method for class 'ordinalbayes'
print(x, ...)

Arguments

x

A fitted ordinalbayes object.

...

other arguments.

Value

Matrix with the summaries from the x$results object which of class 'runjags'. Columns include Lower95, Median, Upper95, Mean, SD, Mode, MCerr, MC%ofSD, SSeff, AC.20, and psrf

Examples


data("cesc")
fit<-ordinalbayes(Stage~1, data=cesc, x=cesc[,5:45],
model="regressvi", gamma.ind="fixed", pi.fixed=0.99, adaptSteps=1000,
burnInSteps=1000, nChains=2, numSavedSteps=2000, thinSteps=2)
print(fit)

Smaller Subset of The Cancer Genome Atlas Cervical Cancer HTSeq Data.

Description

This subset includes 41 transcripts and four phenotypic variables for 242 subjects with squamous cell cervical cancer.

Usage

reducedSet

Format

The format is of formal class 'DESeqTransform' (package "DESeq2") with the following extractor functions:

assay: includes rld transformed transcript expression data
colData: includes phenotypic data: age_at_index, cigarettes_per_day, race, and Stage

Source

TCGAbiolinks TCGA-CESC

Summarize an Ordinal Bayes Object.

Description

Summarize an Ordinal Bayes Object.

Usage

## S3 method for class 'ordinalbayes'
summary(object, epsilon = 0.1, ...)

Arguments

object

A fitted ordinalbayes object.

epsilon

a small positive value that is close to 0 for testing an interval null hypothesis for the beta parameters.

...

other arguments.

Value

alphamatrix

The MCMC output for the threshold parameters.

betamatrix

The MCMC output for the penalized parameters.

zetamatrix

The MCMC output for the unpenalized parameters (if included).

gammamatrix

The MCMC output for the variable inclusion parameters (not available for lasso).

gammamean

The posterior mean of the variable inclusion indicators (not available for lasso)for the variable inclusion indicators (not available for lasso).

gamma.BayesFactor

Bayes factor for the variable inclusion indicators (not available for lasso).

Beta.BayesFactor

Bayes factor for the penalized parameters where the interval null is tested using epsilon.

lambdamatrix

The MCMC output for the penalty parameter (not available for normalss).

Examples


data("cesc")
fit<-ordinalbayes(Stage~1, data=cesc, x=cesc[,5:45],
         model="regressvi", gamma.ind="fixed", pi.fixed=0.99,
         adaptSteps=1000, burnInSteps=1000, nChains=2,
         numSavedSteps=2000, thinSteps=2, seed=26)
summary.fit<-summary(fit)
names(summary.fit)
names(which(summary.fit$Beta.BayesFactor>5))
names(which(summary.fit$gamma.BayesFactor>5))

Data Frame of Smaller Subset of The Cancer Genome Atlas Cervical Cancer HTSeq Data.

Description

Usage

Format

Source

Examples

Extract Model Coefficients

Description

Usage

Arguments

Value

See Also

Examples

Subset of The Cancer Genome Atlas Cervical Cancer HTSeq Data.

Description

Usage

Format

Source

Ordinal Bayesian Regression Models for High-Dimensional Data

Description

Usage

Arguments

Value

See Also

Examples

Trace Plot and/or Density Plot of MCMC Output.

Description

Usage

Arguments

Value

Examples

Predicted Probabilities and Class for an Ordinal Bayes Fit.

Description

Usage

Arguments

Value

See Also

Examples

Print MCMC Summary Statistics

Description

Usage

Arguments

Value

See Also

Examples

Smaller Subset of The Cancer Genome Atlas Cervical Cancer HTSeq Data.

Description

Usage

Format

Source

Summarize an Ordinal Bayes Object.

Description

Usage

Arguments

Value

See Also

Examples