Package: factorana 1.7.1

factorana: Factor Model Estimation with Latent Variables

A flexible framework for estimating factor models with multiple latent variables. Supports linear, probit, ordered probit, and multinomial logit model components. Features include multi-stage estimation, automatic parameter initialization, analytical gradients and Hessians, and parallel estimation. Methods are described in Heckman, Humphries, and Veramendi (2016) <doi:10.1016/j.jeconom.2015.12.001>, Heckman, Humphries, and Veramendi (2018) <doi:10.1086/698760>, and Humphries, Joensen, and Veramendi (2024) <doi:10.1257/pandp.20241026>.

Authors:Greg Veramendi [aut, cre], Jess Xiong [aut]

factorana_1.7.1.tar.gz
factorana_1.7.1.zip(r-4.7-x86_64)factorana_1.7.1.zip(r-4.7-arm64)factorana_1.7.1.zip(r-4.6-x86_64)factorana_1.7.1.zip(r-4.6-arm64)factorana_1.7.1.zip(r-4.5-x86_64)
factorana_1.7.1.tgz(r-4.6-x86_64)factorana_1.7.1.tgz(r-4.6-arm64)factorana_1.7.1.tgz(r-4.5-x86_64)factorana_1.7.1.tgz(r-4.5-arm64)
factorana_1.7.1.tar.gz(r-4.7-arm64)factorana_1.7.1.tar.gz(r-4.7-x86_64)factorana_1.7.1.tar.gz(r-4.6-arm64)factorana_1.7.1.tar.gz(r-4.6-x86_64)
factorana_1.7.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
factorana/json (API)

# Install 'factorana' in R:
install.packages('factorana', repos = c('https://gregveramendi.r-universe.dev', 'https://cloud.r-project.org'))
Uses libs:
  • c++– GNU Standard C++ Library v3

On CRAN:

Conda:

This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.

cpp

3.65 score 10 scripts 357 downloads 38 exports 4 dependencies

Last updated from:4576db4a14. Checks:15 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-arm64OK131
linux-devel-x86_64OK176
source / vignettesOK221
linux-release-arm64OK130
linux-release-x86_64OK140
macos-release-arm64OK162
macos-release-x86_64OK499
macos-oldrel-arm64OK155
macos-oldrel-x86_64OK517
windows-devel-arm64OK403
windows-devel-x86_64OK202
windows-release-arm64OK407
windows-release-x86_64OK167
windows-oldrel-x86_64OK155
wasm-releaseOK107

Exports:bootstrap_factoranabootstrap_factorana_multistagebootstrap_fit_samplebuild_dynamic_previous_stagecleanup_parallel_workerscollect_bootstrapcomponents_tablecomponents_to_latexdefine_dynamic_measurementdefine_estimation_controldefine_factor_modeldefine_model_componentdefine_model_systemdisable_adaptive_quadrature_cppestimate_and_writeestimate_factorscores_rcppestimate_model_rcppevaluate_factorscore_likelihood_cppevaluate_likelihood_cppevaluate_loglik_only_cppevaluate_obs_scores_cppextract_free_params_cppfix_coefficientfix_factor_paramfix_type_interceptsgauss_hermite_quadraturegenerate_bootstrap_samplesget_parameter_info_cppinitialize_factor_model_cppinitialize_parametersresults_tableresults_to_latexrobust_seset_adaptive_quadrature_cppset_observation_weights_cppsimulate_factor_modelvcov_factoranawrite_model_config_csv

Dependencies:MASSnnetRcppRcppEigen

Dynamic Factor Model
Overview | Simulate data | Stage 1: define_dynamic_measurement() | Why we do not pool the intercepts | Stage 2: build_dynamic_previous_stage() + SE_linear | Recovery | Cluster-robust standard errors | Bootstrap for honest two-stage standard errors | Notes on generalisation | Where to go next
Rendered fromdynamic_structural.Rmdusingknitr::rmarkdown

Last update: 2026-06-10
Started: 2026-04-22

Measurement System: Two-Factor CFA
Overview | Simulate data | Define the factor model | Define model components | Estimate | Inspect estimates | Robust standard errors | Factor scores | Simulate from the fitted model | Where to go next
Rendered frommeasurement_system.Rmdusingknitr::rmarkdown

Last update: 2026-06-10
Started: 2026-04-22

Roy Model: Sector Choice with a Latent Ability Factor
Overview | Simulate data | Model specification | Measurement equations (tests) | Potential outcomes (wages) | Sector-choice equation | Assemble the system | Estimation | Results | Robust standard errors | Recover factor scores | Two-stage estimation (optional)
Rendered fromroy_model.Rmdusingknitr::rmarkdown

Last update: 2026-06-10
Started: 2026-04-22

Readme and manuals

Help Manual

Help pageTopics
Single-node bootstrap driver (convenience over the primitives)bootstrap_factorana
Multi-stage single-node bootstrap driverbootstrap_factorana_multistage
Estimate one stage for one bootstrap sample (restartable)bootstrap_fit_sample
Build a Stage 2 previous_stage object from a dynamic measurement fitbuild_dynamic_previous_stage
Clean up orphaned parallel worker processescleanup_parallel_workers
Collect finished bootstrap samples into standard errors and intervalscollect_bootstrap
Create a components table for a single modelcomponents_table
Export components table to LaTeXcomponents_to_latex
Define a dynamic measurement system for longitudinal factor modelsdefine_dynamic_measurement
Define estimation control settingsdefine_estimation_control
Define latent factor model structuredefine_factor_model
Define a model componentdefine_model_component
Define a model systemdefine_model_system
Disable adaptive quadraturedisable_adaptive_quadrature_cpp
Run estimation and write standard output filesestimate_and_write
Estimate Factor Scoresestimate_factorscores_rcpp
Estimate modelestimate_model
Estimate factor model using R-based optimizationestimate_model_rcpp
Evaluate log-likelihood for a single observation at given factor valuesevaluate_factorscore_likelihood_cpp
Evaluate log-likelihood for given parametersevaluate_likelihood_cpp
Evaluate log-likelihood only (for optimization)evaluate_loglik_only_cpp
Per-observation scores for sandwich / cluster-robust standard errorsevaluate_obs_scores_cpp
Extract free parameters from full parameter vectorextract_free_params_cpp
Fix a coefficient in a model componentfix_coefficient
Fix a factor-distribution parameter at model-definition timefix_factor_param
Fix type-specific intercepts to zero for a model componentfix_type_intercepts
Compute Gauss-Hermite quadrature nodes and weightsgauss_hermite_quadrature
Generate and persist bootstrap resampling weightsgenerate_bootstrap_samples
Get parameter counts from FactorModelget_parameter_info_cpp
Initialize a FactorModel C++ object from R model systeminitialize_factor_model_cpp
Initialize parameters for factor model estimationinitialize_parameters
Print method for components_tableprint.components_table
Print method for factorana_factorscoresprint.factorana_factorscores
Print and Summary Methods for Factor Model Resultsprint.factorana_result
Print method for factorana_tableprint.factorana_table
Print method for model_component objectsprint.model_component
Print method for summary.factorana_resultprint.summary.factorana_result
Create a formatted results table for multiple modelsresults_table
Export results table to LaTeXresults_to_latex
Robust / cluster-robust standard errors for a fitted factorana modelrobust_se
Set up adaptive quadrature based on factor scores and standard errorsset_adaptive_quadrature_cpp
Set observation weights for weighted likelihood estimationset_observation_weights_cpp
Simulate data from a factorana modelsimulate_factor_model
Summary method for factorana_result objectssummary.factorana_result
Robust and cluster-robust covariance for a fitted factorana modelvcov_factorana
Write a single CSV with all configuration rowswrite_model_config_csv