Package index • dlmtree

Model fitting

dlmtree(): Fit tree structured distributed lag models

dlmtree.control.diagnose(): Diagnostic control settings for dlmtree model fitting

dlmtree.control.family(): Family control settings for dlmtree model fitting

dlmtree.control.het(): Control settings for dlmtree model fitting, when used for heterogeneous models

dlmtree.control.hyper(): Hyperparameter control settings for dlmtree model fitting

dlmtree.control.mcmc(): MCMC control settings for dlmtree model fitting

dlmtree.control.mix(): Control settings for dlmtree model fitting, when used for mixture models

dlmtree.control.monotone(): Control settings for dlmtree model fitting, when used for monotone model

dlmtree.control.tdlnm(): Control settings for dlmtree model fitting, when used for TDLNM

diagnose(): diagnose

Model summary

Obtain results from the model fit

combine.models(): Combines information from DLMs of single exposure

combine.models.tdlmm(): Combines information from DLMs of mixture exposures.

summary(): summary

estDLM(): Calculates subgroup-specific lag effects for heterogeneous models

ppRange(): Makes a 'pretty' output of a group of numbers

predict(): predict

adj_coexposure(): Adjusting for expected changes in co-exposure (TDLMM)

print(): print

Visualization

Visualize distributed lag functions

plot(<summary.monotone>): Returns variety of plots for model summary of class 'monotone'

plot(<summary.tdlm>): Plots a distributed lag function for model summary of 'tdlm'

plot(<summary.tdlmm>): Plots DLMMs for model summary of class 'tdlmm'

plot(<summary.tdlnm>): Returns variety of plots for model summary of class 'tdlnm'

HDLM & HDLMM

Useful functions for HDLM & HDLMM

pip(): Calculates posterior inclusion probabilities (PIPs) for modifiers in HDLM & HDLMM

shiny(): shiny

splitpoints(): Determines split points for continuous modifiers

Simulation

Simulate datasets

sim.hdlmm(): Creates simulated data for HDLM & HDLMM

sim.tdlmm(): Creates simulated data for TDLM & TDLMM

sim.tdlnm(): Creates simulated data for TDLNM

Data

Built-in datasets

coExp: Randomly sampled exposure from Colorado counties

exposureCov: Exposure covariance structure

pm25Exposures: PM2.5 Exposure data

zinbCo: Time-series exposure data for ZINB simulated data

get_sbd_dlmtree(): Download simulated data for dlmtree articles

Cpp source code & Misc.

cppIntersection(): fast set intersection tool assumes sorted vectors A and B

dlmEst(): Calculates the distributed lag effect with DLM matrix for linear models.

dlmtreeGPFixedGaussian(): dlmtree model with fixed Gaussian process approach

dlmtreeGPGaussian(): dlmtree model with Gaussian process approach

dlmtreeHDLMGaussian(): dlmtree model with shared HDLM approach

dlmtreeHDLMMGaussian(): dlmtree model with HDLMM approach

dlmtreeTDLMFixedGaussian(): dlmtree model with fixed Gaussian approach

dlmtreeTDLMNestedGaussian(): dlmtree model with nested Gaussian approach

dlmtreeTDLM_cpp(): dlmtree model with nested HDLM approach

dlnmEst(): Calculates the distributed lag effect with DLM matrix for non-linear models.

dlnmPLEst(): Calculates the distributed lag effect with DLM matrix for non-linear models.

drawTree(): Draws a new tree structure

mixEst(): Calculates the lagged interaction effects with MIX matrix for linear models.

monotdlnm_Cpp(): dlmtree model with monotone tdlnm approach

ppRange(): Makes a 'pretty' output of a group of numbers

rcpp_pgdraw(): Multiple draw polya gamma latent variable for var c[i] with size b[i]

rtmvnorm(): Truncated multivariate normal sampler, mean mu, cov sigma, truncated (0, Inf)

ruleIdx(): Calculates the weights for each modifier rule

scaleModelMatrix(): Centers and scales a matrix

splitPIP(): Calculates the posterior inclusion probability (PIP).

tdlmm_Cpp(): dlmtree model with tdlmm approach

tdlnm_Cpp(): dlmtree model with tdlnm approach

zeroToInfNormCDF(): Integrates (0,inf) over multivariate normal