Learn R Programming

lame (version 1.3.4)

Longitudinal Additive and Multiplicative Effects Models for Networks

Description

Additive and multiplicative effects models for both cross-sectional and longitudinal network analysis. The package provides two main functions: ame() for cross-sectional networks and lame() for longitudinal networks. It supports square and rectangular network structures. Key features include: (1) Cross-sectional network analysis via ame() with support for binary, continuous, ordinal, and count data; (2) Longitudinal network analysis via lame() with additive sender/receiver and multiplicative latent-factor effects that can evolve over time through AR(1) processes (Sewell and Chen (2015) ; Durante and Dunson (2014) ); (3) Handling of changing actor compositions across time periods in longitudinal models; (4) Performance improvements through C++ implementations via 'Rcpp' and 'RcppArmadillo'.

Copy Link

Version

Install

install.packages('lame')

Version

1.3.4

License

MIT + file LICENSE

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/netify-dev/lame

Homepage

https://netify-dev.github.io/lame/

Maintainer

Shahryar Minhas

Last Published

August 4th, 2026

Functions in lame (1.3.4)

ordinal relational data and covariates

ame_memory_usage

Calculate memory usage of AME model components

Refit a fast AME model with a warm start

Convert array to list.

ame_als_bootstrap

Bootstrap uncertainty for the fast AME estimator

AME model fitting options

AME model fitting routine

ame_memory_settings

Display memory usage information for AME models

Run AME model with multiple parallel chains

Fast (MCMC-free) AME estimation for a cross-sectional network

Generic dispatcher for posterior::as_draws on lame fits

Convert a graph object to a lame-ready adjacency matrix

bipartite_helpers

Bipartite network helper functions

boot_ame-no-fitted

fitted/residuals are not defined for a bootstrap object

Validate input data format for lame function

coef.als_dynamic_beta

Extract beta path from a penalised-ALS object

Convert an AME / LAME fit to a posterior draws object

Bayesian credible intervals for AME model parameters

compute_XtX_Xty_bip_cpp

Compute X'X and X'y for bipartite covariate regression

confint.ame_als

Confidence intervals for a fast AME fit

Optimize AME model output for memory efficiency

autoplot.ame_als

autoplot method for ALS fits

compute_mcmc_diagnostics

Compute MCMC convergence diagnostics for multiple chains

Point estimates from a fast AME bootstrap

combine_ame_chains

Combine multiple AME chains

Extract coefficients from a fast AME fit

Ribbon plot of time-varying coefficients (or coefplot for static fits)

Extract model coefficients from AME model

design_array_listwisedel

Computes the design socioarray of covariate values

.build_full_design

Build the full canonical design for a newdata prediction

compute_gof_bipartite

Compute GOF statistics for bipartite networks

.actor_ffbs_path

Univariate Carter-Kohn FFBS for one actor's length-T slope path

detect_change_point

Detect potential change points in a dynamic_beta posterior path

.ame_propagate_cov_na

Propagate covariate missingness into the response

.exact_center_per_actor

Exact variance-weighted sum-to-zero projection for the per-actor block

.reorder_newdata_actors

Realign a newdata covariate array to the fit's internal actor order

confint.boot_ame

Confidence intervals from a fast AME bootstrap

Assemble the dyadic design socioarray for an AME model

Extract fitted values from a fast AME fit

Extract fitted values from AME model

.fit_actor_order

The fit's internal (canonical) actor order

dynamic_beta_prior_summary

Summarise the implied prior on a time-varying coefficient path

Edgelist to sociomatrix

evaluate_heldout

Held-out predictive evaluation for an ame / lame fit

.rotation_drift_diagnostic

Rotation-drift diagnostic for the canonical (U_t, G_t, V_t) trio

.sweep_per_actor_exact

Per-actor sweep: unconstrained per-actor FFBS + exact projection

Forward-filter / backward-sample for vec(G_t) under AR(1) state prior

Glance method for fitted ame_als / lame_als objects

Glance method for fitted ame / lame objects

Get fitted object from MCMC results

Get fitted object from MCMC results

Create design array for replicate data

Probability-integral-transform calibration check for h-step forecasts

Dutch college data

Extract fitted values from LAME model

S3 generic for glance

get_EZ_dynamic_beta_cpp

Compute EZ when beta is time-varying

formula() is not defined for an ame() / lame() fit

init_dynamic_positions

Initialize dynamic latent positions with AR(1) structure

Compute GOF statistics from saved posterior samples

Posterior-predictive temporal-trend test

init_dynamic_ab_cpp

Initialize dynamic additive effects with AR(1) structure

Goodness of fit statistics

gof_plot.ame_als

Goodness-of-fit check for an ame_als fit

latent_positions

Extract latent positions as a tidy data frame

Visualize goodness-of-fit statistics for AME and LAME models

Longitudinal Additive and Multiplicative Effects Models for Networks

gof_stats_bipartite

Goodness of fit statistics for bipartite networks

Name-safe linear predictor from a newdata prediction

Convert list to array

Exact rolling-origin leave-future-out cross-validation

Lazega's law firm data

gof_stats_unipartite

Goodness of fit statistics for unipartite networks

Fast (MCMC-free) AME estimation for a longitudinal network

Multi-panel lame() with shared coefficients

Generic dispatcher for loo / waic on ame / lame fits

Approximate leave-one-out cross-validation for AME / LAME fits

Number of observed dyads in an AME / LAME fit

Run LAME (longitudinal AME) with multiple parallel chains

Symmetric square root of a matrix

Numerically stable log(Phi(hi) - Phi(lo))

AME model fitting routine for longitudinal relational data

Log-likelihood is not directly exposed for ame() / lame() fits

Fast approximate dynamic snap-shift AME estimator

list_to_array_bipartite

Convert bipartite list data to array format

Log-likelihood is not defined for a fast AME fit

per_actor_slopes

Post-MCMC per-actor time-varying slopes

Resume a lame() MCMC run from a checkpoint

posterior_options

Options for saving posterior samples during MCMC

Simple diagnostic plot for AME model fit

Print method for AME model objects

print.als_dynamic_beta

Print method for penalised ALS time-varying beta

Print method for LAME objects

posterior_quantiles

Extract posterior quantiles for model components

print.gof_temporal

Print method for gof_temporal output

ERGM-style covariate helpers for ame() / lame()

Print the priors used by an AME / LAME / ame_als fit

Print methods for AME and LAME simulation objects

Plot the convergence of a fast AME fit

Number of observed dyads in an ame_als fit

Gibbs update for additive effects covariance

Plot diagnostics for a LAME model fit

Gibbs update for multiplicative effects covariance

predict.ame_als

Predictions from a fast AME fit

Predict method for LAME models

Precompute design-array cross-product summaries

rUV_dynamic_bip_fc_cpp

Bipartite dynamic UV Gibbs update

print.lame_multi

Print method for lame_multi

Gibbs sampling of U and V

rUV_dynamic_t_fc_cpp

Update dynamic latent positions with heavy-tailed (Student-t) AR(1) innovations

print.summary.ame_als

Print a fast AME summary

print.summary.ame

Print method for summary.ame objects

Print bootstrap results for a fast AME fit

Print an ame_als object

print.per_actor_slopes

Print method for per_actor_slopes

Predict method for AME models

prediction_draws_long

Long-format draws of the linear predictor for marginaleffects-style use

Print method for lfo() results

Gibbs sampling of U and V

Gibbs sampling of U and V from replicated relational data

print.summary.lame

Print method for summary.lame objects

rUV_dynamic_fc_cpp

Update dynamic latent positions using AR(1) process

Gibbs sampling of dynamic U and V with AR(1) evolution

rZ_bin_bip_batch_cpp

Batch binary Z sampling across all time periods (bipartite, rho=0)

rUV_dynamic_snap_fc

Gibbs sampling of dynamic U and V with snap-shift dynamics

Draw latent Z for the binary probit model

procrustes_align

Procrustes alignment of latent positions across time

Draw the latent Z matrix for fixed-rank-nomination data

Sample Z under bipartite fixed-rank nominations (rectangular)

Draw latent Z for censored-binary nomination data

Full-conditional latent draw for the ordinal family

Sample Z under bipartite censored binary nominations (rectangular)

rUV_dynamic_t_fc

Gibbs sampling of dynamic U and V with heavy-tailed (Student-t) innovations

rUV_dynamic_snap_fc_cpp

Update dynamic latent positions with snap-shift model selection

rZ_ord_sym_explicit_fc

Symmetric ordinal Z sample given explicit cutpoints (R >= 0 safe)

rZ_ord_explicit_fc

Sample Z given explicit cutpoints alpha (asymmetric ordinal)

Sample Z under bipartite ordinal data (rectangular)

rZ_nrm_batch_cpp

Batch normal Z sampling across all time periods

Simulate missing values in a normal AME model

Gibbs update for latent variable in a Poisson AME model

rbeta_ab_bip_gibbs_cpp

Full bipartite Gibbs update for beta, a, b

Read the per-iteration log-lik matrix back from on-disk chunks

Extract residuals from LAME model

Extract residuals from AME model

Sample Z under symmetric ordinal data (square symmetric matrix)

rbeta_ab_rep_fc

Gibbs update of regression coefficients and additive effects for replicated relational data

Gibbs update for dyadic variance

Sample Z under bipartite Poisson (rectangular MH step)

Joint Gibbs update of regression and additive effects (single relation)

Sample additive row effects and their covariance for the binary family

rhat_dynamic_beta

Multivariate split-R-hat for dynamic_beta coefficient paths

Full-conditional draw of the dyadic variance for replicated relational data

residuals.ame_als

Residuals from a fast AME fit

Simulation from a multivariate normal distribution

sample_beta_dynamic_cpp

Sample the dynamic-block beta path via FFBS

Reconstruct EZ and UVPM matrices from AME model output

Objects exported from other packages

Simulate a and Sab from full conditional distributions under frn likelihood

Metropolis-Hastings update for the within-dyad correlation

Simulate a and Sab from full conditional distributions under the cbin likelihood

sample_ab_bipartite

Sample additive effects for bipartite networks

sample_beta_static_cpp

Sample the static-block beta conditional on the dynamic path

sample_dynamic_ab_cpp

Sample dynamic additive effects with AR(1) evolution

rtnorm_interval_logp

Exact truncated-normal draw on (lb, ub) via the log.p-scale inverse CDF

Simulation from a Wishart distribution

sample_alpha_cowles

Cowles MH update for explicit ordinal cutpoints (Z-marginalised)

sample_rho_ab_cpp

Sample AR(1) parameter for dynamic additive effects

sample_rho_beta_cpp

Sample the AR(1) rho for each dynamic block

sample_sigma_ab_cpp

Sample innovation variance for dynamic additive effects

sample_sigma_beta_cpp

Sample the AR(1) innovation sigma for each dynamic block

sample_sigma_G2

Inverse-gamma posterior draw for sigma_G^2 given the FFBS path

Sheep dominance data

Sample AR(1) parameter for dynamic latent factors

sample_sigma_uv

Sample innovation variance for dynamic latent factors

sampler_describe

Describe the estimator behind a fitted object

Simulate a Poisson relational matrix

Simulate networks from a fitted AME model

simulate.ame_als

Simulate networks from a fitted ame_als model

snap_category_summary

Summarize snap indices by actor category

Sampson's monastery data

Simulate a latent relational Gaussian array

Sociomatrix to edgelist

sample_rho_G_mh

Logit-scale MH update on the AR(1) coefficient rho_G

Simulate a binary relational matrix from latent means

Simulate a relational matrix under a fixed rank nomination scheme

Simulate longitudinal networks from a fitted LAME model

simulate_posterior

Simulate posterior distributions from fitted AME model

summary.lame.sim

Summary method for LAME simulations

summary.ame.sim

Summary method for AME simulations

snap_index_summary

Summarize posterior snap indices

snap_rank_summary

Summarize posterior rank uncertainty for snap years

snap_index_draws

Extract posterior draws of snap indices

Summary of an AME object

summary.ame_als

Summarize an ame_als object

Simulate an ordinal relational matrix

Simulate a normal relational matrix

Update an AME / LAME fit

Tidy method for a standalone bootstrap object (boot_ame)

Tidy method for fitted ame / lame objects

update_variances_bipartite

Update variance parameters for bipartite

S3 generic for tidy

Update an ame_als / lame_als fit

Sandwich covariance for the regression coefficients of a fast AME fit

Posterior covariance of AME model coefficients

MCMC trace plots and density plots for AME/LAME model parameters

Summary of a LAME object

summary.boot_ame

Summarize bootstrap results for a fast AME fit

rank-based z-scores

WAIC for AME / LAME fits

Bootstrap covariance of the regression coefficients

TIES sanctions data for vignettes

Visualize multiplicative effects (latent factors) from AME models

Tidy method for fitted ame_als / lame_als objects

Relational matrix

International relations in the 90s

Compute Xbeta product for bipartite networks

Linear combinations of submatrices of an array

ab_plot.ame_als

Additive-effects plot for an ame_als fit

Convert an ALS fit to MCMC starting values

als_dynamic_beta

Penalised ALS time-varying coefficient estimate

binary relational data and covariates

Synthetic longitudinal binary relational data, list-form (latent-scale)

AddHealth community 3 data

Column covariates

Dyadic covariates

Visualize sender and receiver random effects

synthetic longitudinal binary relational data (latent-scale)

Fixed rank nomination data and covariates

Censored binary nomination data and covariates

normal relational data and covariates

AddHealth community 9 data