Package: postcard 1.1.0.9000

Mathias Lerbech Jeppesen

postcard: Estimating Marginal Effects with Prognostic Covariate Adjustment

Conduct power analyses and inference of marginal effects. Uses plug-in estimation and influence functions to perform robust inference, optionally leveraging historical data to increase precision with prognostic covariate adjustment. The methods are described in Højbjerre-Frandsen et al. (2025) <doi:10.48550/arXiv.2503.22284>.

Authors:Mathias Lerbech Jeppesen [aut, cre], Emilie Hojbjerre-Frandsen [aut], Novo Nordisk A/S [cph]

postcard_1.1.0.9000.tar.gz
postcard_1.1.0.9000.zip(r-4.7-any)postcard_1.1.0.9000.zip(r-4.6-any)postcard_1.1.0.9000.zip(r-4.5-any)
postcard_1.1.0.9000.tgz(r-4.6-any)postcard_1.1.0.9000.tgz(r-4.5-any)
postcard_1.1.0.9000.tar.gz(r-4.7-any)postcard_1.1.0.9000.tar.gz(r-4.6-any)
postcard_1.1.0.9000.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
postcard/json (API)

# Install 'postcard' in R:
install.packages('postcard', repos = c('https://novonordisk-opensource.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/novonordisk-opensource/postcard/issues

Pkgdown/docs site:https://novonordisk-opensource.github.io

On CRAN:

Conda:

5.08 score 2 stars 10 scripts 250 downloads 15 exports 111 dependencies

Last updated from:b8c3587bb3. Checks:7 NOTE, 2 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-develNOTE194
source / vignettesOK259
linux-releaseNOTE204
macos-releaseNOTE165
macos-oldrelNOTE136
windows-develNOTE158
windows-releaseNOTE156
windows-oldrelNOTE161
wasm-releaseOK131

Exports:default_learnersestestimandfit_best_learnerglm_datapower_gspower_marginaleffectpower_ncprogrctglmrctglm_with_prognosticscorerepeat_power_linearrepeat_power_marginaleffectsamplesize_gsvariance_ancova

Dependencies:base64encbslibcachemclasscliclockcodetoolscpp11data.tableDerivdiagramdialsDiceDesigndigestdplyrearthevaluatefarverfastmapfontawesomeFormulafsfurrrfuturefuture.applyGauProgenericsgggridggplot2globalsgluegowergtablehardhathighrhtmltoolsipredisobandjquerylibjsonliteKernSmoothknitrlabelinglatticelavalbfgslifecyclelistenvlubridatemagrittrMASSMatrixmemoisemimemixoptmodelenvnnetnumDerivoptionsparallellyparsnippillarpkgconfigplotmoplotrixprettyunitsprodlimprogressrpurrrR6rappdirsRColorBrewerRcppRcppArmadillorecipesrlangrmarkdownrpartrsampleS7sassscalessfdshapeslidersparsevctrssplitfngrSQUAREMstringistringrsurvivaltailortibbletidyrtidyselecttimechangetimeDatetinytextunetzdbutf8vctrsviridisLitewarpwithrworkflowsworkflowsetsxfunxgboostyamlyardstick

Controlling behavior of model fitting functions
Generating some data to run examples | Controlling verbosity | Specifying the estimand | Built-in estimands - average treatment effect and rate ratio | Specifying any estimand | Variance estimation using cross validation | Prognostic covariate adjustment | Specifying learners | Default learners | Creating own list of learners | Inspecting the prognostic model
Rendered frommodel-fit.Rmdusingknitr::rmarkdown

Last update: 2025-09-15
Started: 2025-03-25

Introduction to postcard
Plug-in estimation of marginal effects and variance estimation using influence functions | Simulating data for exploratory analyses | Fitting rctglm() without prognostic covariate adjustment | Using prognostic covariate adjustment | Investigating the prognostic model | Prospective power approximation | For marginal effects | For linear models | Creating a plot of prospective power curves | Using repeat_power_marginaleffect() and plotting the results
Rendered frompostcard.Rmdusingknitr::rmarkdown

Last update: 2025-09-15
Started: 2025-03-28

Prospective Power Estimation
Estimating the power for marginal effects | Simulating some data | Controlling assumptions
Rendered fromprospective-power.Rmdusingknitr::rmarkdown

Last update: 2025-09-15
Started: 2025-03-25