Cyclops: Cyclic coordinate descent for logistic, Poisson and survival analysis

Description

The Cyclops package incorporates cyclic coordinate descent and majorization-minimization approaches to fit a variety of regression models found in large-scale observational healthcare data. Implementations focus on computational optimization and fine-scale parallelization to yield efficient inference in massive datasets.

Author(s)

Maintainer: Marc A. Suchard msuchard@ucla.edu

Authors:

• Martijn J. Schuemie

• Trevor R. Shaddox

• Yuxi Tian

• Jianxiao Yang

• Eric Kawaguchi

Other contributors:

• Sushil Mittal [contributor]

• Observational Health Data Sciences and Informatics [copyright holder]

• Marcus Geelnard (provided the TinyThread library) [copyright holder, contributor]

• Rutgers University (provided the HParSearch routine) [copyright holder, contributor]

• R Development Core Team (provided the ZeroIn routine) [copyright holder, contributor]

See Also

Useful links:

• https://github.com/ohdsi/cyclops

• Report bugs at https://github.com/ohdsi/cyclops/issues

Create a multitype outcome object

Description

Multitype creates a multitype outcome object, usually used as a response variable in a hierarchical Cyclops model fit.

Usage

Multitype(y, type)

Arguments

Value

An object of class Multitype with length equal to the length of y and type.

Examples

Multitype(c(0,1,0), as.factor(c("A","A","B")))

Asymptotic confidence intervals for a fitted Cyclops model object

Description

aconfinit constructs confidence intervals of arbitrary level using asymptotic standard error estimates.

Usage

aconfint(
  object,
  parm,
  level = 0.95,
  control,
  overrideNoRegularization = FALSE,
  ...
)

Arguments

Value

A matrix with columns reporting lower and upper confidence limits for each parameter. These columns are labelled as (1-level) / 2 and 1 - (1 - level) / 2 in % (by default 2.5% and 97.5%)

appendSqlCyclopsData

Description

appendSqlCyclopsData appends data to an OHDSI data object.

Usage

appendSqlCyclopsData(
  object,
  oStratumId,
  oRowId,
  oY,
  oTime,
  cRowId,
  cCovariateId,
  cCovariateValue
)

Arguments

Details

Append data using two tables. The outcomes table is dense and contains ... The covariates table is sparse and contains ... All entries in the outcome table must be sorted in increasing order by (oStratumId, oRowId). All entries in the covariate table must be sorted in increasing order by (cRowId). Each cRowId value must match exactly one oRowId value.

Place Cyclops model fit object in a persistent cache

Description

cacheCyclopsModelForJava places a Cyclops model fit object into a persistent cache, so that the object may be used across language-barriers.

Usage

cacheCyclopsModelForJava(object)

Arguments

Value

Integer index of object in persistent cache

Clear the Cyclops persistent cache

Description

clearCyclopsModelCache clears the persistent cache holding Cyclops model fit objects that may be used across language-barriers.

Usage

clearCyclopsModelCache()

Extract model coefficients

Description

coef.cyclopsFit extracts model coefficients from an Cyclops model fit object

Usage

## S3 method for class 'cyclopsFit'
coef(object, rescale = FALSE, ignoreConvergence = FALSE, ...)

Arguments

Value

Named numeric vector of model coefficients.

Confidence intervals for Cyclops model parameters

Description

confinit.cyclopsFit profiles the data likelihood to construct confidence intervals of arbitrary level. Usually it only makes sense to do this for variables that have not been regularized.

Usage

## S3 method for class 'cyclopsFit'
confint(
  object,
  parm,
  level = 0.95,
  overrideNoRegularization = FALSE,
  includePenalty = TRUE,
  rescale = FALSE,
  maximumCurvature = -0.001,
  ...
)

Arguments

Value

A matrix with columns reporting lower and upper confidence limits for each parameter. These columns are labelled as (1-level) / 2 and 1 - (1 - level) / 2 in percent (by default 2.5 percent and 97.5 percent)

Examples

#Generate some simulated data:
sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
                           model = "poisson")
cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
                                    addIntercept = TRUE)

#Define the prior and control objects to use cross-validation for finding the 
#optimal hyperparameter:
prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
control <- createControl(cvType = "auto", noiseLevel = "quiet")

#Fit the model
fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  

#Find out what the optimal hyperparameter was:
getHyperParameter(fit)

#Extract the current log-likelihood, and coefficients
logLik(fit)
coef(fit)

#We can only retrieve the confidence interval for unregularized coefficients:
confint(fit, c(0))

Convert data from two data frames or ffdf objects into a CyclopsData object

Description

convertToCyclopsData loads data from two data frames or ffdf objects, and inserts it into a Cyclops data object.

Usage

convertToCyclopsData(
  outcomes,
  covariates,
  modelType = "lr",
  timeEffectMap = NULL,
  addIntercept = TRUE,
  checkSorting = NULL,
  checkRowIds = TRUE,
  normalize = NULL,
  quiet = FALSE,
  floatingPoint = 64
)

## S3 method for class 'data.frame'
convertToCyclopsData(
  outcomes,
  covariates,
  modelType = "lr",
  timeEffectMap = NULL,
  addIntercept = TRUE,
  checkSorting = NULL,
  checkRowIds = TRUE,
  normalize = NULL,
  quiet = FALSE,
  floatingPoint = 64
)

## S3 method for class 'tbl_dbi'
convertToCyclopsData(
  outcomes,
  covariates,
  modelType = "lr",
  timeEffectMap = NULL,
  addIntercept = TRUE,
  checkSorting = NULL,
  checkRowIds = TRUE,
  normalize = NULL,
  quiet = FALSE,
  floatingPoint = 64
)

Arguments

Details

These columns are expected in the outcome object:

These columns are expected in the covariates object:

These columns are expected in the timeEffectMap object:

Value

An object of type cyclopsData

Methods (by class)

• convertToCyclopsData(data.frame): Convert data from two data.frame

• convertToCyclopsData(tbl_dbi): Convert data from two Andromeda tables

Examples

#Convert infert dataset to Cyclops format:
covariates <- data.frame(stratumId = rep(infert$stratum, 2),
                         rowId = rep(1:nrow(infert), 2),
                         covariateId = rep(1:2, each = nrow(infert)),
                         covariateValue = c(infert$spontaneous, infert$induced))
outcomes <- data.frame(stratumId = infert$stratum,
                       rowId = 1:nrow(infert),
                       y = infert$case)
#Make sparse:
covariates <- covariates[covariates$covariateValue != 0, ]

#Create Cyclops data object:
cyclopsData <- convertToCyclopsData(outcomes, covariates, modelType = "clr",
                                    addIntercept = FALSE)

#Fit model:
fit <- fitCyclopsModel(cyclopsData, prior = createPrior("none"))

Convert to Cyclops Prior Variance

Description

convertToCyclopsVariance converts the regularization parameter lambda from glmnet into a prior variance.

Usage

convertToCyclopsVariance(lambda, nobs)

Arguments

Value

Prior variance under a Laplace() prior

Convert to glmnet regularization parameter

Description

convertToGlmnetLambda converts a prior variance from Cyclops into the regularization parameter lambda.

Usage

convertToGlmnetLambda(variance, nobs)

Arguments

Value

lambda

Convert short sparse covariate table to long sparse covariate table for time-varying coefficients.

Description

convertToTimeVaryingCoef convert short sparse covariate table to long sparse covariate table for time-varying coefficients.

Usage

convertToTimeVaryingCoef(shortCov, longOut, timeVaryCoefId)

Arguments

Details

These columns are expected in the shortCov object:

These columns are expected in the longOut object:

Value

A long sparse covariate table for time-varying coefficients.

Coverage

Description

coverage computes the coverage on confidence intervals

Usage

coverage(goldStandard, lowerBounds, upperBounds)

Arguments

Value

The proportion of times goldStandard falls between lowerBound and upperBound

Create a Cyclops control object that supports multiple hyperparameters

Description

createCrossValidationControl creates a Cyclops control object for use with fitCyclopsModel that supports multiple hyperparameters through an auto-search in one dimension and a grid-search over the remaining dimensions

Usage

createAutoGridCrossValidationControl(
  outerGrid,
  autoPosition = 1,
  refitAtMaximum = TRUE,
  cvType = "auto",
  initialValue = 1,
  ...
)

Arguments

Value

A Cyclops prior object of class inheriting from "cyclopsPrior" and "cyclopsFunctionalPrior" for use with fitCyclopsModel.

Create a Cyclops control object

Description

createControl creates a Cyclops control object for use with fitCyclopsModel.

Usage

createControl(
  maxIterations = 1000,
  tolerance = 1e-06,
  convergenceType = "gradient",
  cvType = "auto",
  fold = 10,
  lowerLimit = 0.01,
  upperLimit = 20,
  gridSteps = 10,
  cvRepetitions = 1,
  minCVData = 100,
  noiseLevel = "silent",
  threads = 1,
  seed = NULL,
  resetCoefficients = FALSE,
  startingVariance = -1,
  useKKTSwindle = FALSE,
  tuneSwindle = 10,
  selectorType = "auto",
  initialBound = 2,
  maxBoundCount = 5,
  algorithm = "ccd",
  doItAll = TRUE,
  syncCV = FALSE
)

Arguments

Value

A Cyclops control object of class inheriting from "cyclopsControl" for use with fitCyclopsModel.

Examples

#Generate some simulated data:
sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
                           model = "poisson")
cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
                                    addIntercept = TRUE)

#Define the prior and control objects to use cross-validation for finding the 
#optimal hyperparameter:
prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
control <- createControl(cvType = "auto", noiseLevel = "quiet")

#Fit the model
fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  

#Find out what the optimal hyperparameter was:
getHyperParameter(fit)

#Extract the current log-likelihood, and coefficients
logLik(fit)
coef(fit)

#We can only retrieve the confidence interval for unregularized coefficients:
confint(fit, c(0))

Create a Cyclops data object

Description

createCyclopsData creates a Cyclops data object from an R formula or data matrices.

Usage

createCyclopsData(
  formula,
  sparseFormula,
  indicatorFormula,
  modelType,
  data,
  subset = NULL,
  weights = NULL,
  censorWeights = NULL,
  offset = NULL,
  time = NULL,
  pid = NULL,
  y = NULL,
  type = NULL,
  dx = NULL,
  sx = NULL,
  ix = NULL,
  model = FALSE,
  normalize = NULL,
  floatingPoint = 64,
  method = "cyclops.fit"
)

Arguments

Details

This function creates a Cyclops model data object from R "formula" or directly from numeric vectors and matrices to define the model response and covariates. If specifying a model using a "formula", then the left-hand side define the model response and the right-hand side defines dense covariate terms. Objects provided with "sparseFormula" and "indicatorFormula" must be include left-hand side responses and terms are coersed into sparse and indicator representations for computational efficiency.

Items to discuss:

• Only use formula or (y,dx,...)

• stratum() in formula

• offset() in formula

• when "stratum" (renamed from pid) are necessary

• when "time" are necessary

Value

A list that contains a Cyclops model data object pointer and an operation duration

Models

Currently supported model types are:

Examples

## Dobson (1990) Page 93: Randomized Controlled Trial :
counts <- c(18, 17, 15, 20, 10, 20, 25, 13, 12)
outcome <- gl(3, 1, 9)
treatment <- gl(3, 3)
cyclopsData <- createCyclopsData(
     counts ~ outcome + treatment,
     modelType = "pr")
cyclopsFit <- fitCyclopsModel(cyclopsData)

cyclopsData2 <- createCyclopsData(
     counts ~ outcome,
     indicatorFormula = ~ treatment,
     modelType = "pr")
summary(cyclopsData2)
cyclopsFit2 <- fitCyclopsModel(cyclopsData2)

Create a Cyclops prior object that returns the MLE of non-separable coefficients

Description

createNonSeparablePrior creates a Cyclops prior object for use with fitCyclopsModel.

Usage

createNonSeparablePrior(maxIterations = 10, ...)

Arguments

Value

A Cyclops prior object of class inheriting from "cyclopsPrior" for use with fitCyclopsModel.

Examples

prior <- createNonSeparablePrior()

Create a Cyclops parameterized prior object

Description

createParameterizedPrior creates a Cyclops prior object for use with fitCyclopsModel in which arbitrary R functions parameterize the prior location and variance.

Usage

createParameterizedPrior(
  priorType,
  parameterize,
  values,
  useCrossValidation = FALSE,
  forceIntercept = FALSE
)

Arguments

Value

A Cyclops prior object of class inheriting from "cyclopsPrior" and "cyclopsFunctionalPrior" for use with fitCyclopsModel.

Create a Cyclops prior object

Description

createPrior creates a Cyclops prior object for use with fitCyclopsModel.

Usage

createPrior(
  priorType,
  variance = 1,
  exclude = c(),
  graph = NULL,
  neighborhood = NULL,
  useCrossValidation = FALSE,
  forceIntercept = FALSE
)

Arguments

Value

A Cyclops prior object of class inheriting from "cyclopsPrior" for use with fitCyclopsModel.

Prior types

We specify all priors in terms of their variance parameters. Similar fitting tools for regularized regression often parameterize the Laplace distribution in terms of a rate "lambda" per observation. See "glmnet", for example.

variance = 2 * / (nobs * lambda)^2 or lambda = sqrt(2 / variance) / nobs

Examples

#Generate some simulated data:
sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
                           model = "poisson")
cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
                                    addIntercept = TRUE)

#Define the prior and control objects to use cross-validation for finding the 
#optimal hyperparameter:
prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
control <- createControl(cvType = "auto", noiseLevel = "quiet")

#Fit the model
fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  

#Find out what the optimal hyperparameter was:
getHyperParameter(fit)

#Extract the current log-likelihood, and coefficients
logLik(fit)
coef(fit)

#We can only retrieve the confidence interval for unregularized coefficients:
confint(fit, c(0))

Create a Cyclops control object that supports in- / out-of-sample hyperparameter search using weights

Description

createWeightBasedSearchControl creates a Cyclops control object for use with fitCyclopsModel that supports hyperparameter optimization through an auto-search where weight = 1 identifies in-sample observations and weight = 0 identifies out-of-sample observations.

Usage

createWeightBasedSearchControl(cvType = "auto", initialValue = 1, ...)

Arguments

Value

A Cyclops prior object of class inheriting from "cyclopsControl" for use with fitCyclopsModel.

Get full path to installed Cyclops library

Description

cyclopsLibraryFileName returns the full path to the installed Cyclops .so/.dll file

Usage

cyclopsLibraryFileName()

Value

String

finalizeSqlCyclopsData

Description

finalizeSqlCyclopsData finalizes a Cyclops data object

Usage

finalizeSqlCyclopsData(
  object,
  addIntercept = FALSE,
  useOffsetCovariate = NULL,
  offsetAlreadyOnLogScale = FALSE,
  sortCovariates = FALSE,
  makeCovariatesDense = NULL
)

Arguments

Fit a Cyclops model

Description

fitCyclopsModel fits a Cyclops model data object

Usage

fitCyclopsModel(
  cyclopsData,
  prior = createPrior("none"),
  control = createControl(),
  weights = NULL,
  forceNewObject = FALSE,
  returnEstimates = TRUE,
  startingCoefficients = NULL,
  fixedCoefficients = NULL,
  warnings = TRUE,
  computeDevice = "native"
)

Arguments

Details

This function performs numerical optimization to fit a Cyclops model data object.

Value

A list that contains a Cyclops model fit object pointer and an operation duration

Prior

Currently supported prior types are:

References

Suchard MA, Simpson SE, Zorych I, Ryan P, Madigan D. Massive parallelization of serial inference algorithms for complex generalized linear models. ACM Transactions on Modeling and Computer Simulation, 23, 10, 2013.

Simpson SE, Madigan D, Zorych I, Schuemie M, Ryan PB, Suchard MA. Multiple self-controlled case series for large-scale longitudinal observational databases. Biometrics, 69, 893-902, 2013.

Mittal S, Madigan D, Burd RS, Suchard MA. High-dimensional, massive sample-size Cox proportional hazards regression for survival analysis. Biostatistics, 15, 207-221, 2014.

Examples

## Dobson (1990) Page 93: Randomized Controlled Trial :
counts <- c(18,17,15,20,10,20,25,13,12)
outcome <- gl(3,1,9)
treatment <- gl(3,3)
cyclopsData <- createCyclopsData(counts ~ outcome + treatment, modelType = "pr")
cyclopsFit <- fitCyclopsModel(cyclopsData, prior = createPrior("none"))
coef(cyclopsFit)
confint(cyclopsFit, c("outcome2","treatment3"))
predict(cyclopsFit)

Fit simulated data

Description

fitCyclopsSimulation fits simulated Cyclops data using Cyclops or a standard routine. This function is useful for simulation studies comparing the performance of Cyclops when considering large, sparse datasets.

Usage

fitCyclopsSimulation(
  sim,
  useCyclops = TRUE,
  model = "logistic",
  coverage = TRUE,
  includePenalty = FALSE,
  computeDevice = "native"
)

Arguments

Get covariate identifiers

Description

getCovariateIds returns a vector of integer64 covariate identifiers in a Cyclops data object

Usage

getCovariateIds(object)

Arguments

Get covariate types

Description

getCovariateTypes returns a vector covariate types in a Cyclops data object

Usage

getCovariateTypes(object, covariateLabel)

Arguments

Get cross-validation information from a Cyclops model fit

Description

getCrossValidationInfo returns the predicted optimal cross-validation point and ordinate

Usage

getCrossValidationInfo(object)

Arguments

Compute predictive log-likelihood from a Cyclops model fit

Description

getCyclopsPredictiveLogLikelihood returns the log-likelihood of a subset of the data in a Cyclops model fit object.

Usage

getCyclopsPredictiveLogLikelihood(object, weights)

Arguments

Value

The predictive log-likelihood

Profile likelihood for Cyclops model parameters

Description

getCyclopsProfileLogLikelihood evaluates the profile likelihood at a grid of parameter values.

Usage

getCyclopsProfileLogLikelihood(
  object,
  parm,
  x = NULL,
  bounds = NULL,
  tolerance = 0.001,
  initialGridSize = 10,
  maxResets = 10,
  includePenalty = TRUE,
  optimalWarmStart = TRUE,
  returnDerivatives = FALSE
)

Arguments

Value

A data frame containing the profile log likelihood. Returns NULL when the adaptive profiling fails to converge.

Creates a Surv object that forces in competing risks and the IPCW needed for Fine-Gray estimation.

Description

getFineGrayWeights creates a list Surv object and vector of weights required for estimation.

Usage

getFineGrayWeights(ftime, fstatus, cvweights = NULL, cencode = 0, failcode = 1)

Arguments

Value

A list that returns both an object of class Surv that forces in the competing risks indicators and a vector of weights needed for parameter estimation.

Examples

ftime <- c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)
fstatus <- c(1, 2, 0, 1, 2, 0, 1, 2, 0, 1)
getFineGrayWeights(ftime, fstatus, cencode = 0, failcode = 1)

Get floating point size

Description

getFloatingPointSize returns the floating-point representation size in a Cyclops data object

Usage

getFloatingPointSize(object)

Arguments

Get hyperparameter

Description

getHyperParameter returns the current hyper parameter in a Cyclops model fit object

Usage

getHyperParameter(object)

Arguments

Examples

#Generate some simulated data:
sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
                           model = "poisson")
cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
                                    addIntercept = TRUE)

#Define the prior and control objects to use cross-validation for finding the 
#optimal hyperparameter:
prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
control <- createControl(cvType = "auto", noiseLevel = "quiet")

#Fit the model
fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  

#Find out what the optimal hyperparameter was:
getHyperParameter(fit)

#Extract the current log-likelihood, and coefficients
logLik(fit)
coef(fit)

#We can only retrieve the confidence interval for unregularized coefficients:
confint(fit, c(0))

Get total number of covariates

Description

getNumberOfCovariates returns the total number of covariates in a Cyclops data object

Usage

getNumberOfCovariates(object)

Arguments

Get total number of rows

Description

getNumberOfRows returns the total number of outcome rows in a Cyclops data object

Usage

getNumberOfRows(object)

Arguments

Get number of strata

Description

getNumberOfStrata return the number of unique strata in a Cyclops data object

Usage

getNumberOfStrata(object)

Arguments

Get total number of outcome types

Description

getNumberOfTypes returns the total number of outcome types in a Cyclops data object

Usage

getNumberOfTypes(object)

Arguments

Extract standard errors

Description

getSEs extracts asymptotic standard errors for specific covariates from a Cyclops model fit object.

Usage

getSEs(object, covariates)

Arguments

Details

This function first computes the (partial) Fisher information matrix for just the requested covariates and then returns the square root of the diagonal elements of the inverse of the Fisher information matrix. These are the asymptotic standard errors when all possible covariates are included. When the requested covariates do not equate to all coefficients in the model, then interpretation is more challenging.

Value

Vector of standard error estimates

Get univariable correlation

Description

getUnivariableCorrelation reports covariates that have high correlation with the outcome

Usage

getUnivariableCorrelation(cyclopsData, covariates = NULL, threshold = 0)

Arguments

Value

A list of covariates whose absolute correlation with the outcome is greater than or equal to the threshold

Get univariable linear separability

Description

getUnivariableSeparability reports covariates that are univariably separable with the outcome

Usage

getUnivariableSeparability(cyclopsData, covariates = NULL)

Arguments

Value

A list of covariates that are univariably separable with the outcome

Extract gradient

Description

gradient returns the current gradient wrt the regression parameters of the log-likelihood of the fit in a Cyclops model fit object

Usage

gradient(object)

Arguments

Check if a Cyclops data object is initialized

Description

isInitialized determines if an Cyclops data object is properly initialized and remains in memory. Cyclops data objects do not serialized/deserialize their back-end memory across R sessions.

Usage

isInitialized(object)

Arguments

List available GPU devices

Description

listGPUDevices list available GPU devices

Usage

listGPUDevices()

Extract log-likelihood

Description

logLik returns the current log-likelihood of the fit in a Cyclops model fit object

Usage

## S3 method for class 'cyclopsFit'
logLik(object, ...)

Arguments

Examples

#Generate some simulated data:
sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
                           model = "poisson")
cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
                                    addIntercept = TRUE)

#Define the prior and control objects to use cross-validation for finding the 
#optimal hyperparameter:
prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
control <- createControl(cvType = "auto", noiseLevel = "quiet")

#Fit the model
fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  

#Find out what the optimal hyperparameter was:
getHyperParameter(fit)

#Extract the current log-likelihood, and coefficients
logLik(fit)
coef(fit)

#We can only retrieve the confidence interval for unregularized coefficients:
confint(fit, c(0))

Calculates xbar*beta

Description

meanLinearPredictor computes xbar*beta for model fit

Usage

meanLinearPredictor(cyclopsFit)

Arguments

Mean squared error

Description

mse computes the mean squared error between two numeric vectors

Usage

mse(goldStandard, estimates)

Arguments

Value

MSE(goldStandard, estimates)

Oxford self-controlled case series data

Description

A dataset containing the MMR vaccination / meningitis in Oxford example from Farrington and Whitaker. There are 10 patients comprising 38 unique exposure intervals.

Usage

data(oxford)

Format

A data frame with 38 rows and 6 variables:

indiv

patient identifier

event

number of events in interval

interval

interval length in days

agegr

age group

exgr

exposure group

loginterval

log interval length

...

Plot Cyclops simulation model fit

Description

plotCyclopsSimulationFit generates a plot that compares goldStandard coefficients to their Cyclops model fit.

Usage

plotCyclopsSimulationFit(fit, goldStandard, label)

Arguments

Model predictions

Description

predict.cyclopsFit computes model response-scale predictive values for all data rows

Usage

## S3 method for class 'cyclopsFit'
predict(object, newOutcomes, newCovariates, ...)

Arguments

Print a Cyclops data object

Description

print.cyclopsData displays information about a Cyclops data model object.

Usage

## S3 method for class 'cyclopsData'
print(x, show.call = TRUE, ...)

Arguments

Print a Cyclops model fit object

Description

print.cyclopsFit displays information about a Cyclops model fit object

Usage

## S3 method for class 'cyclopsFit'
print(x, show.call = TRUE, ...)

Arguments

Print Cyclops data matrix to file

Description

printMatrixMarket prints the data matrix to a file

Usage

printMatrixMarket(object, file)

Arguments

Read Cyclops data from file

Description

readCyclopsData reads a Cyclops-formatted text file.

Usage

readCyclopsData(fileName, modelType)

Arguments

Details

This function reads a Cyclops-formatted text file and returns a Cyclops data object. The first line of the file may start with '‘⁠#⁠’', indicating that it contains header options. Valid header options are:

Successive lines of the file are white-space delimited and follow the format:

	[Row ID] {Stratum ID} [Weight] <Outcome> {Censored} {Offset} <BBR covariates>

• ⁠[optional]⁠

• ⁠<required>⁠

• ⁠{required or optional depending on model}⁠

Bayesian binary regression (BBR) covariates are white-space delimited and generally in a sparse ‘⁠<name>:<value>⁠’ format, where ‘⁠name⁠’ must (currently) be numeric and ‘⁠value⁠’ is non-zero. If option ‘⁠indicator_only⁠’ is specified, then format is simply ‘⁠<name>⁠’. ‘⁠Row ID⁠’ and ‘⁠Stratum ID⁠’ must be numeric, and rows must be sorted such that equal ‘⁠Stratum ID⁠’ are consecutive. ‘⁠Stratum ID⁠’ is required for ‘⁠clr⁠’ and ‘⁠sccs⁠’ models. ‘⁠Censored⁠’ is required for a ‘⁠cox⁠’ model. ‘⁠Offset⁠’ is (currently) required for a ‘⁠sccs⁠’ model.

Value

A list that contains a Cyclops model data object pointer and an operation duration

Models

Currently supported model types are:

Examples

## Not run: 
dataPtr = readCyclopsData(system.file("extdata/infert_ccd.txt", package="Cyclops"), "clr")

## End(Not run)

Apply simple data reductions

Description

reduce reports the count of non-zero elements, sum and sum-of-squares for specified covariates in a Cyclops data object.

Usage

reduce(object, covariates, groupBy, power = 1)

Arguments

Value

Specified reduction as number or data.frame if segmented.

Model residuals

Description

residuals.cyclopsFit computes model residuals for Cox model-based Cyclops objects

Usage

## S3 method for class 'cyclopsFit'
residuals(object, parm = NULL, type = "schoenfeld", ...)

Arguments

Run bootstrap for Cyclops model parameters

Description

Run bootstrap for Cyclops model parameters

Usage

runBootstrap(object, replicates, ciCoverage = 0.95, na.rm = FALSE)

Arguments

Set GPU device

Description

setOpenCLDevice set GPU device

Usage

setOpenCLDevice(name)

Arguments

Simulation Cyclops dataset

Description

simulateCyclopsData generates a simulated large, sparse data set for use by fitCyclopsSimulation.

Usage

simulateCyclopsData(
  nstrata = 200,
  nrows = 10000,
  ncovars = 20,
  effectSizeSd = 1,
  zeroEffectSizeProp = 0.9,
  eCovarsPerRow = ncovars/100,
  model = "survival"
)

Arguments

Value

A simulated data set

Examples

#Generate some simulated data:
sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
                           model = "poisson")
cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
                                    addIntercept = TRUE)

#Define the prior and control objects to use cross-validation for finding the 
#optimal hyperparameter:
prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
control <- createControl(cvType = "auto", noiseLevel = "quiet")

#Fit the model
fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  

#Find out what the optimal hyperparameter was:
getHyperParameter(fit)

#Extract the current log-likelihood, and coefficients
logLik(fit)
coef(fit)

#We can only retrieve the confidence interval for unregularized coefficients:
confint(fit, c(0))

Split the analysis time into several intervals for time-varying coefficients.

Description

splitTime split the analysis time into several intervals for time-varying coefficients

Usage

splitTime(shortOut, cut)

Arguments

Value

A long outcome table for time-varying coefficients.

Cyclops data object summary

Description

summary.cyclopsData summarizes the data held in an Cyclops data object.

Usage

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

Arguments

Value

Returns a data.frame that reports simply summarize statistics for each covariate in a Cyclops data object.

Calculate baseline hazard function

Description

survfit.cyclopsFit computes baseline hazard function

Usage

## S3 method for class 'cyclopsFit'
survfit(formula, type = "aalen", ...)

Arguments

Value

Baseline survival function for mean covariates

Test hazard ratio proportionality assumption

Description

testProportionality tests the hazard ratio proportionality assumption of a Cyclops model fit object

Usage

testProportionality(object, parm = NULL, transformedTimes)

Arguments

Calculate variance-covariance matrix for a fitted Cyclops model object

Description

vcov.cyclopsFit returns the variance-covariance matrix for all covariates of a Cyclops model object

Usage

## S3 method for class 'cyclopsFit'
vcov(object, control, overrideNoRegularization = FALSE, ...)

Arguments

Value

A matrix of the estimates covariances between all covariate estimates.