Package: ddtlcm 0.2.1

Mengbing Li

ddtlcm: Latent Class Analysis with Dirichlet Diffusion Tree Process Prior

Implements a Bayesian algorithm for overcoming weak separation in Bayesian latent class analysis. Reference: Li et al. (2023) <arxiv:2306.04700>.

Authors:Mengbing Li [cre, aut], Briana Stephenson [ctb], Zhenke Wu [ctb]

ddtlcm_0.2.1.tar.gz
ddtlcm_0.2.1.zip(r-4.5)ddtlcm_0.2.1.zip(r-4.4)ddtlcm_0.2.1.zip(r-4.3)
ddtlcm_0.2.1.tgz(r-4.4-any)ddtlcm_0.2.1.tgz(r-4.3-any)
ddtlcm_0.2.1.tar.gz(r-4.5-noble)ddtlcm_0.2.1.tar.gz(r-4.4-noble)
ddtlcm_0.2.1.tgz(r-4.4-emscripten)ddtlcm_0.2.1.tgz(r-4.3-emscripten)
ddtlcm.pdf |ddtlcm.html✨
ddtlcm/json (API)
NEWS

# Install 'ddtlcm' in R:

install.packages('ddtlcm', repos = c('https://limengbinggz.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/limengbinggz/ddtlcm/issues

Datasets:

data_synthetic - Synthetic data example
parameter_diet - Parameters for the HCHS dietary recall data example
result_diet_1000iters - Result of fitting DDT-LCM to a semi-synthetic data example

On CRAN:

5.72 score 5 stars 8 scripts 148 downloads 19 exports 139 dependencies

Last updated 4 months agofrom:e012957499. Checks:OK: 1 NOTE: 6. Indexed: yes.

Target	Result	Date
Doc / Vignettes	OK	Nov 23 2024
R-4.5-win	NOTE	Nov 23 2024
R-4.5-linux	NOTE	Nov 23 2024
R-4.4-win	NOTE	Nov 23 2024
R-4.4-mac	NOTE	Nov 23 2024
R-4.3-win	NOTE	Nov 23 2024
R-4.3-mac	NOTE	Nov 23 2024

Exports:A_t_inv_one A_t_inv_two a_t_one a_t_one_cum a_t_two a_t_two_cum compute_IC create_leaf_cor_matrix ddtlcm_fit expit initialize logit plot_tree_with_barplot plot_tree_with_heatmap random_detach_subtree simulate_DDT_tree simulate_lcm_given_tree simulate_lcm_response simulate_parameter_on_tree

Dependencies:abind ade4 ape aplot askpass backports BayesLogit boot brio broom callr car carData cli colorspace combinat commonmark corrplot cowplot cpp11 crayon curl data.table Deriv desc diffobj digest doBy dplyr evaluate extraDistr fansi farver Formula fs generics ggfun ggplot2 ggplotify ggpubr ggrepel ggsci ggsignif ggtext ggtree glue gridExtra gridGraphics gridtext gtable hms httr isoband jpeg jsonlite label.switching labeling lattice lazyeval lifecycle lme4 lpSolve magrittr markdown MASS Matrix MatrixModels matrixStats mgcv microbenchmark mime minqa modelr munsell nlme nloptr nnet numDeriv openssl patchwork pbkrtest phylobase pillar pixmap pkgbuild pkgconfig pkgload plyr png poLCA polynom praise prettyunits processx progress ps purrr quantreg R.methodsS3 R.oo R.utils R6 rbibutils RColorBrewer Rcpp RcppArmadillo RcppEigen Rdpack reshape2 rlang rncl RNeXML rprojroot rstatix scales scatterplot3d sp SparseM stringi stringr survival sys testthat tibble tidyr tidyselect tidytree treeio truncnorm utf8 uuid vctrs viridisLite waldo withr xfun XML xml2 yulab.utils

Vignettes for ddtlcm: An R package for fitting tree-regularized Bayesian latent class models

Rendered fromddtlcm-demo.Rmdusingknitr::rmarkdownon Nov 23 2024.

Last update: 2024-03-26
Started: 2023-08-24

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
Compute divergence function	A_t_inv_one a_t_one a_t_one_cum
Compute divergence function	A_t_inv_two a_t_two a_t_two_cum
Add a leaf branch to an existing tree tree_old	add_leaf_branch
Add a leaf branch to an existing tree tree_old to make a multichotomus branch	add_multichotomous_tip
Functions to simulate trees and node parameters from a DDT process. Add a branch to an existing tree according to the branching process of DDT	add_one_sample
Add a singular root node to an existing nonsingular tree	add_root
Attach a subtree to a given DDT at a randomly selected location	attach_subtree
Compute information criteria for the DDT-LCM model	compute_IC
Create a tree-structured covariance matrix from a given tree	create_leaf_cor_matrix
Synthetic data example	data_synthetic
MH-within-Gibbs sampler to sample from the full posterior distribution of DDT-LCM	ddtlcm_fit
Sample divergence time on an edge uv previously traversed by m(v) data points	div_time
Efficiently sample multivariate normal using precision matrix from x ~ N(Q^{-1}a, Q^{-1}), where Q^{-1} is the precision matrix	draw_mnorm
Compute normalized probabilities: exp(x_i) / sum_j exp(x_j)	exp_normalize
The expit function	expit
Harmonic series	H_n
Initialize the MH-within-Gibbs algorithm for DDT-LCM	initialize
Estimate an initial binary tree on latent classes using hclust()	initialize_hclust
Estimate an initial response profile from latent class model using poLCA()	initialize_poLCA
Provide a random initial response profile based on latent class mode	initialize_randomLCM
Compute factor in the exponent of the divergence time distribution	J_n
Numerically accurately compute f(x) = log(x / (1/x)).	log_expit
The logistic function	logit
Calculate loglikelihood of a DDT, including the tree structure and node parameters	logllk_ddt
Calculate loglikelihood of the DDT-LCM	logllk_ddt_lcm
Compute loglikelihood of divergence times for a(t) = c/(1-t)	logllk_div_time_one
Compute loglikelihood of divergence times for a(t) = c/(1-t)^2	logllk_div_time_two
Calculate loglikelihood of the latent class model, conditional on tree structure	logllk_lcm
Compute log likelihood of parameters	logllk_location
Compute loglikelihood of the tree topology	logllk_tree_topology
Parameters for the HCHS dietary recall data example	parameter_diet
Plot the MAP tree and class profiles (bar plot) of summarized DDT-LCM results	plot_tree_with_barplot
Plot the MAP tree and class profiles (heatmap) of summarized DDT-LCM results	plot_tree_with_heatmap
Create trace plots of DDT-LCM parameters	plot.ddt_lcm
Plot the MAP tree and class profiles of summarized DDT-LCM results	plot.summary.ddt_lcm
Prediction of class memberships from posterior predictive distributions	predict.ddt_lcm
Prediction of class memberships from posterior summaries	predict.summary.ddt_lcm
Print out setup of a ddt_lcm model	print.ddt_lcm
Print out summary of a ddt_lcm model	print.summary.ddt_lcm
Calculate proposal likelihood	proposal_log_prob
Suppress print from cat()	quiet
Metropolis-Hasting algorithm for sampling tree topology and branch lengths from the DDT branching process.	random_detach_subtree
Attach a subtree to a given DDT at a randomly selected location	reattach_point
Result of fitting DDT-LCM to a semi-synthetic data example	result_diet_1000iters
Sample divergence function parameter c for a(t) = c / (1-t) through Gibbs sampler	sample_c_one
Sample divergence function parameter c for a(t) = c / (1-t)^2 through Gibbs sampler	sample_c_two
Sample individual class assignments Z_i, i = 1, ..., N	sample_class_assignment
Sample the leaf locations and Polya-Gamma auxilliary variables	sample_leaf_locations_pg
Sample item group-specific variances through Gibbs sampler	sample_sigmasq
Sample a new tree topology using Metropolis-Hastings through randomly detaching and re-attaching subtrees	sample_tree_topology
Simulate a tree from a DDT process. Only the tree topology and branch lengths are simulated, without node parameters.	simulate_DDT_tree
Simulate multivariate binary responses from a latent class model given a tree	simulate_lcm_given_tree
Simulate multivariate binary responses from a latent class model	simulate_lcm_response
Simulate node parameters along a given tree.	simulate_parameter_on_tree
Summarize the output of a ddt_lcm model	summary.ddt_lcm
Compute WAIC	WAIC