Movatterモバイル変換

[0]ホーム
URL:

Title:Conditional Binary Quantile Models
Version:0.2.0.4
Author:Xiao Lu [aut, cre]
Maintainer:Xiao Lu <xiao.lu.research@gmail.com>
Description:Estimates conditional binary quantile models developed by Lu (2020) <doi:10.1017/pan.2019.29>. The estimation procedure is implemented based on Markov chain Monte Carlo methods.
License:MIT + file LICENSE
Encoding:UTF-8
Biarch:true
Depends:R (≥ 3.4.0)
Imports:methods, Formula, Rcpp (≥ 0.12.0), rstan (≥ 2.18.1),rstantools (≥ 2.0.0)
LinkingTo:BH (≥ 1.66.0), Rcpp (≥ 0.12.0), RcppEigen (≥ 0.3.3.3.0),rstan (≥ 2.18.1), StanHeaders (≥ 2.18.0)
SystemRequirements:GNU make
RoxygenNote:7.1.2
NeedsCompilation:yes
Packaged:2025-03-06 14:28:38 UTC; xiao
Repository:CRAN
Date/Publication:2025-03-06 17:50:02 UTC

cbq: An R Package for Estimating Conditional Binary Quantile Models

Description

Bayesian estimation of conditional binary quantile models.

References

Lu, Xiao. (2020). Discrete Choice Data with Unobserved Heterogeneity: A Conditional Binary Quantile Model. Political Analysis, 28(2), 147-167. https://doi.org/10.1017/pan.2019.29

Stan Development Team (2019). RStan: the R interface to Stan. R package version 2.19.2. https://mc-stan.org

Fitting conditional binary quantile models

Description

The main function for running the conditional binary quantile model. The function returns a cbqcbq object that can be further investigated using standard functions such asplot,print,coef, andpredict.

Usage

cbq(  formula,  data,  q = NULL,  vi = FALSE,  nsim = 1000,  grad_samples = 1,  elbo_samples = 100,  tol_rel_obj = 0.01,  output_samples = 2000,  burnin = NULL,  thin = 1,  CIsize = 0.95,  nchain = 1,  seeds = 12345,  inverse_distr = FALSE,  offset = 1e-20,  mc_core = TRUE)

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.

data

A data frame containing the variables in the model.

q

The quantile value.

vi

Indicating whether variantional inference should be used instead of MCMC sampling procedure.

nsim

The number of iterations.

grad_samples

Passed tovb (positive integer), the number of samples for Monte Carlo estimate of gradients, defaulting to 1.

elbo_samples

Passed tovb (positive integer), the number of samples for Monte Carlo estimate of ELBO (objective function), defaulting to 100. (ELBO stands for "the evidence lower bound".)

tol_rel_obj

Passed tovb (positive double), the convergence tolerance on the relative norm of the objective, defaulting to 0.01.

output_samples

Passed tovb (positive integer), number of posterior samples to draw and save, defaults to 1000.

burnin

The number of burnin iterations.

thin

Thinning parameter.

CIsize

The size of confidence interval.

nchain

The number of parallel chains.

seeds

Random seeds to replicate the results.

inverse_distr

If FALSE, the ALD will not be reversed. The default is FALSE.

offset

Offset values to enhance sampling stability. The default value is 1e-20.

mc_core

Indicating whether the estimation will be run in multiple parallel chains. The default is TRUE.

Details

The model can be passed either as a combination of aformula and a data framedata, as inlm().

Convergence diagnotics can be performed using eitherprint(object, "mcmc") orplot(object, "mcmc").

Value

Acbq object, which can be further analyzed with its associatedplot.cbq,coef.cbq andprint.cbq functions.

An object of classcbq contains the following elements

Call

The matched call.

formula

Symbolic representation of the model.

q

The quantile value.

nsim

The number of MCMC iterations.

burnin

The number of burnin periods.

thin

Thinning.

seeds

Random seeds.

CIsize

The size of confidence interval.

data

Data used.

x

Covaraites used.

y

The dependent variable.

xnames

Names of the covariates.

stanfit

Outputs from stan.

sampledf

A matrix of posterior samples.

summaryout

A summary based on posterior samples.

npars

Number of covariates.

ulbs

Lower and upper confidence bounds.

means

Estimates at the mean.

vi

Indicating whether variational inference has been performed.

output_samples

Sample outputs.

fixed_var

Variables estimated using fixed effects.

random_var

Variables estimated using random effects.

xq

Variables indicating the choice sets.

Author(s)

Xiao Lu

References

Lu, Xiao. (2020). Discrete Choice Data with Unobserved Heterogeneity: A Conditional Binary Quantile Model. Political Analysis, 28(2), 147-167. https://doi.org/10.1017/pan.2019.29

Examples

# Simulate the datax <- rnorm(50)y <- ifelse(x > 0, 1, 0)dat <- as.data.frame(cbind(y, x))# Estimate the CBQ modelmodel <- cbq(y ~ x, dat, 0.5, nchain = 1, mc_core = FALSE)# Show the resultsprint(model)coef(model)plot(model)

Extract CBQ Coefficients

Description

Create a table of coefficient results from acbq object.

Usage

## S3 method for class 'cbq'coef(object, ...)

Arguments

object

Acbq object.

...

Further arguments passed to or from other methods.

Value

A table of coefficients with their corresponding lower and upper bounds.

Probability density function of asymmetric Laplace distributions

Description

dald calculates probability densities of asymmetric Laplace distributions.

Usage

dald(x, mu, p, sigma)

Arguments

x

Random variable.

mu

Position parameter.

p

Quantile.

sigma

Scale parameter.

Value

probability density ofx.

Inverse function

Description

inverse generates inverse function of any given function.

Usage

inverse(f, mu, p, sigma, lower = -10000, upper = 10000)

Arguments

f

pald function

mu

Position parameter.

p

Quantile.

sigma

Scale parameter.

lower

Lower bound.

upper

Upper bound.

Value

inversed pald

Check if a predictor is dichotomous, adopted from packagecircGLM

Description

Check if a predictor is dichotomous, adopted from packagecircGLM

Usage

is.dichotomous(x)

Arguments

x

A character or numerical vector to be tested.

Value

A logical,TRUE if thex has dummy coding (0, 1),FALSE otherwise.

Cumulative density function of asymmetric Laplace distributions

Description

pald calculates cumulative densities of asymmetric Laplace distributions.

Usage

pald(x, mu, p, sigma)

Arguments

x

Random variable.

mu

Position parameter.

p

Quantile.

sigma

Scale parameter.

Value

cumulative probability density ofx.

Plot cbq object

Description

General plot function forcbq objects, which dispatches the chosentype of plotting to the corresponding function.

Usage

## S3 method for class 'cbq'plot(x, type = "trace", ...)

Arguments

x

Acbq object to be plotted.

type

Character string giving the type of plotting. The options are"trace" for trace plots,"coef" for coefficient plots. The default is the traceplot.

...

Additional arguments to be passed to subsequent plot functions.

Value

None.

Make coefficient plots for cbq

Description

Plot traceplots from acbq object.

Usage

plot_coef.cbq(object, ...)

Arguments

object

Acbq object.

...

Additional parameters to be passed to the plot function.

Value

None.

Make traceplots for cbq

Description

Plot traceplots from acbq object.

Usage

plot_trace.cbq(object, ...)

Arguments

object

Acbq object.

...

Additional parameters to be passed to the traceplot function.

Value

None.

Predictions based on the fitted parameter values

Description

Create a vector of predictions from acbq object.

Usage

## S3 method for class 'cbq'predict(object, data, ci = 0.95, ...)

Arguments

object

Acbq object.

data

Data used for prediction.

ci

Confidence interval. The default is 0.95.

...

Further arguments passed to or from other methods.

Value

A vector of predictions.

Print cbq object

Description

General print function forcbq objects, which dispatches the chosen typeof printing to the corresponding function.

Usage

## S3 method for class 'cbq'print(x, type = "text", ...)

Arguments

x

Acbq object to be printed.

type

Character string giving the type of printing, such as"text","mcmc","coef".

...

Additional arguments to be passed to print functions.

Value

None.

Description

Print cbq coefficients

Usage

print_coef.cbq(object, digits = 3)

Arguments

object

Acbq object.

digits

Number of digits to display.

Value

None.

Description

This prints a number of diagnostics about the results of acbq objects

Usage

print_mcmc.cbq(object, ...)

Arguments

object

Acbq object.

...

Additional arguments to be passed to the print function.

Value

None.

Description

Print the main results from acbq object.

Usage

print_text.cbq(object, digits = 3)

Arguments

object

Acbq object.

digits

Number of digits to display.

Quantile function of asymmetric Laplace distributions

Description

qald calculates quantiles values of asymmetric Laplace distributions.

Usage

qald(y, mu, p, sigma)

Arguments

y

quantile value.

mu

Position parameter.

p

Quantile.

sigma

Scale parameter.

Value

quantile value.

Random number generator of asymmetric Laplace distributions

Description

rald generates random numbers from asymmetric Laplace distributions.

Usage

rald(n, mu, p, sigma)

Arguments

n

Number of random numbers to be generated.

mu

Position parameter.

p

Quantile.

sigma

Scale parameter.

Value

random numbers.

[8]ページ先頭
©2009-2025 Movatter.jp