450: Add horseshoe prior, as well as constant prior by danielinteractive · Pull Request #472 · Genentech/jmpost

danielinteractive · 2026-07-09T07:42:00Z

closes #450

* slight tangent: add prior_const for surv exp first as a try * first matching comparison between jmpost and brms for horseshoe prior usage * first try to reduce to one model.stan file * let Prior handle parameter declaration in the Stan code together with limits * adapt documentation * add snapshot tests for model stan code construction * add vignette * few fixes

prior_cauchy(), prior_gamma(), prior_invgamma(), prior_loglogistic(), prior_lognormal()

…rseshoe prior) to avoid warnings about uninitialized parameters

github-actions · 2026-07-09T08:01:32Z

Code Coverage Summary

Filename                           Stmts    Miss  Cover    Missing
-------------------------------  -------  ------  -------  ------------------------------
R/brier_score.R                      173       1  99.42%   272
R/DataJoint.R                         78       0  100.00%
R/DataLongitudinal.R                 126       1  99.21%   251
R/DataSubject.R                       85       1  98.82%   144
R/DataSurvival.R                     106       0  100.00%
R/defaults.R                          13       9  30.77%   17-59, 86
R/generics.R                          40       5  87.50%   53, 431, 452, 515, 533
R/Grid.R                              27       1  96.30%   183
R/GridEven.R                          36       0  100.00%
R/GridEvent.R                         22       0  100.00%
R/GridFixed.R                         30       0  100.00%
R/GridGrouped.R                       54       0  100.00%
R/GridManual.R                        23       3  86.96%   79-81
R/GridObserved.R                      24       0  100.00%
R/GridPopulation.R                    37       4  89.19%   66, 74-76
R/GridPrediction.R                    37       6  83.78%   85, 93-97
R/JointModel.R                       131       9  93.13%   148-153, 203, 207, 252, 325
R/JointModelSamples.R                 96       0  100.00%
R/link_generics.R                     39      16  58.97%   67-70, 93-96, 115-118, 141-144
R/Link.R                              66       4  93.94%   202-205
R/LinkComponent.R                     24       3  87.50%   92, 121-122
R/LongitudinalClaretBruno.R          123       6  95.12%   221-225, 244
R/LongitudinalGSF.R                  138       0  100.00%
R/LongitudinalModel.R                 29       2  93.10%   68, 70
R/LongitudinalQuantities.R            74       0  100.00%
R/LongitudinalRandomEffects.R         65      17  73.85%   86-111
R/LongitudinalRandomSlope.R           62       6  90.32%   139-143, 156
R/LongitudinalSteinFojo.R            117      10  91.45%   204-208, 247-251
R/Parameter.R                         60       0  100.00%
R/ParameterList.R                     62       1  98.39%   209
R/populationHR.R                      63       0  100.00%
R/Prior.R                            494       6  98.79%   421, 453, 948, 1120-1125
R/Promise.R                           29       0  100.00%
R/Quantities.R                        61       0  100.00%
R/QuantityGeneratorPopulation.R       23       0  100.00%
R/QuantityGeneratorPrediction.R       48       0  100.00%
R/QuantityGeneratorSubject.R          21       0  100.00%
R/settings.R                          14      14  0.00%    59-75
R/SimGroup.R                           5       0  100.00%
R/SimJointData.R                     180      10  94.44%   133, 302-310
R/SimLongitudinal.R                    5       2  60.00%   22, 41
R/SimLongitudinalClaretBruno.R       107       0  100.00%
R/SimLongitudinalGSF.R               107       0  100.00%
R/SimLongitudinalRandomSlope.R        55       0  100.00%
R/SimLongitudinalSteinFojo.R          77       0  100.00%
R/SimSurvival.R                      165       0  100.00%
R/simulate.R                         364     364  0.00%    47-551
R/StanModel.R                         16       0  100.00%
R/StanModule.R                       186       6  96.77%   202-203, 247, 258, 409, 437
R/SurvivalExponential.R               15       0  100.00%
R/SurvivalGamma.R                     17       0  100.00%
R/SurvivalLoglogistic.R               17       0  100.00%
R/SurvivalModel.R                     20       0  100.00%
R/SurvivalQuantities.R               172       1  99.42%   127
R/SurvivalWeibullPH.R                 25       0  100.00%
R/utilities.R                        149       2  98.66%   15, 351
R/zzz.R                               31      28  9.68%    3-7, 9-32, 39-48
TOTAL                               4463     538  87.95%

Diff against main

Filename                   Stmts    Miss  Cover
-----------------------  -------  ------  --------
R/DataSurvival.R              +3       0  +100.00%
R/generics.R                  +4       0  +1.39%
R/JointModelSamples.R        +15       0  +100.00%
R/Parameter.R                +46       0  +100.00%
R/ParameterList.R            +20       0  +0.77%
R/Prior.R                   +149      -2  +1.10%
R/SurvivalExponential.R       +1       0  +100.00%
R/SurvivalLoglogistic.R       +2       0  +100.00%
TOTAL                       +240      -2  +0.73%

Results for commit: 9576e1d

Minimum allowed coverage is 80%

♻️ This comment has been updated with latest results

github-actions · 2026-07-09T08:28:42Z

Unit Tests Summary

1 files 208 suites 11m 2s ⏱️
186 tests 170 ✅ 16 💤 0 ❌
1 248 runs 1 230 ✅ 18 💤 0 ❌

Results for commit 9576e1d.

♻️ This comment has been updated with latest results.

github-actions · 2026-07-09T08:28:46Z

Unit Test Performance Difference

Test Suite	$Status$	Time on `main`	$±Time$	$±Tests$	$±Skipped$	$±Failures$	$±Errors$
LongitudinalRandomEffects	💚	$91.15$	$-39.75$	$0$	$0$	$0$	$0$
initialValues	💚	$1.23$	$-1.01$	$0$	$0$	$0$	$0$
misc_models	💚	$16.78$	$-16.78$	$+3$	$0$	$0$	$0$
model_multi_chain	💚	$61.39$	$-21.56$	$0$	$0$	$0$	$0$
survival_plot	💔	$0.98$	$+1.26$	$+2$	$-1$	$0$	$0$

Additional test case details

Test Suite	$Status$	Time on `main`	$±Time$	Test Case
DataSurvival	👶		$+0.00$	model.matrix_for_DataSurvival_preserves_no_intercept_formulas
Grid	💚	$105.73$	$-68.68$	Grid_objects_work_with_QuantityGenerator_and_QuantityCollapser
JointModel	💔	$2.80$	$+2.31$	JointModel_smoke_tests
JointModel	👶		$+0.00$	JointModel_snapshots_assembled_parameter_declarations
JointModelSamples	💔	$11.47$	$+22.29$	print_works_as_expected_for_JointModelSamples
LongitudinalClaretBruno	💚	$1934.08$	$-1926.12$	LongitudinalClaretBruno_works_as_expected_with_default_arguments
LongitudinalGSF	💚	$1719.79$	$-1710.59$	LongitudinalGSF_works_as_expected_with_default_arguments
LongitudinalQuantiles	💚	$50.01$	$-32.27$	Test_that_LongitudinalQuantities_works_as_expected
LongitudinalRandomEffects	💚	$91.15$	$-39.75$	LongitudinalRandomEffects_works_as_expected
LongitudinalRandomSlope	💚	$86.72$	$-84.33$	Print_method_for_LongitudinalRandomSlope_works_as_expected
LongitudinalSteinFojo	💚	$1743.28$	$-1733.19$	LongitudinalSteinFojo_works_as_expected_with_default_arguments
Parameter	👶		$+0.00$	Parameter_declaration_blocks_depend_on_prior_const
Parameter	👶		$+0.00$	Parameter_declaration_helpers_render_Stan_code
Prior	👶		$+0.00$	default_auxiliary_prior_methods_return_empty_lists
Prior	👶		$+0.01$	prior_const_works_as_expected
Prior	👶		$+0.01$	prior_horseshoe_works_as_expected
Prior	👶		$+0.02$	redundant_positive_support_prior_truncation_is_omitted
SimSurvival	💚	$4.28$	$-3.53$	SimSurvivalExponential_creates_a_dataset_with_the_correct_parameter
SurvivalExponential	💚	$73.15$	$-72.45$	Can_load_and_compile_SurvivalExponential_model
SurvivalExponential	👶		$+0.01$	SurvivalExponential_can_fix_lambda_with_prior_const_
SurvivalExponential	👶		$+0.00$	SurvivalExponential_does_not_print_truncation_for_prior_const_
SurvivalGamma	💚	$222.31$	$-220.23$	Print_method_for_SurvivalGamma_works_as_expected
SurvivalLoglogistic	💚	$44.02$	$-42.88$	Can_load_and_compile_SurvivalLogLogistic_model
SurvivalQuantities	💚	$102.45$	$-41.81$	SurvivalQuantities_and_autoplot.SurvivalQuantities_works_as_expected
SurvivalWeibullPH	💚	$15.23$	$-13.48$	Print_method_for_SurvivalWeibullPH_works_as_expected
brierScore	💚	$63.07$	$-58.61$	brierScore_SurvivalQuantities_returns_same_results_as_survreg
brms_compare	👶		$+0.02$	jmpost_and_brms_get_similar_horseshoe_estimates_for_survival_models
brms_compare	💚	$353.18$	$-353.08$	jmpost_and_brms_get_similar_loo_for_longitudinal_models
initialValues	👶		$+0.01$	initialValues_includes_auxiliary_prior_parameters
initialValues	💚	$3.64$	$-1.27$	initialValues_works_as_expected
initialValues	💚	$1.23$	$-1.01$	initial_values_for_fixed_distributions_gives_valid_values
misc_models	💔	$16.78$	$+141.99$	Longitudinal_Model_doesn_t_print_sampler_rejection_messages
misc_models	👶		$+0.00$	Survival_model_can_be_fit_with_a_horseshoe_prior
model_multi_chain	💚	$61.39$	$-21.56$	Can_recover_known_distribution_parameters_from_random_slope_model_when_using_multiple_chains
populationHR	💚	$30.50$	$-11.71$	populationHR_works_as_expected_for_default_parameters
simulate	💚	$267.85$	$-267.77$	simulate_works_with_default_options
stan_functions	💔	$1.47$	$+47.30$	GSF_SLD_function_works_as_expected
survival_plot	💔	$0.98$	$+1.26$	survival_plot_works_as_expected

Results for commit 67741ab

♻️ This comment has been updated with latest results.

danielinteractive and others added 26 commits July 7, 2026 14:29

fix math printing in design doc

6311e73

add stats spec

7e42866

add prior_horseshoe - first stab

a6bd3ec

explain syntax test part

874f7c6

add a test for it

a5f31d2

add shrinkage factors as transformed parameters

f0fe614

make sure all shrinkage factors in samples

daabd53

add covariates and shrinkage gen. functions and methods, run docs

064c551

first stab at comparison with brms but does not run yet

5fa4f38

fix model.matrix for models without intercept

bd6099a

set lambda effectively to 1 in jmpost comparison with brms

0ad5437

truncation, functions

4654f95

move shrinkage factor calc to generated quantities to save sampling time

59d5a4d

ensure to return empty stan module for empty prior to avoid warning

6fe5096

some test fixes

caa20e6

some fixes

cef0a6e

fix prior_const printing

355db42

prior-aware dispatch for render_stan_limits(), so T[0, ] is omitted for:

ea9007b

prior_cauchy(), prior_gamma(), prior_invgamma(), prior_loglogistic(), prior_lognormal()

updates to tests

1dde042

fix one test

77f7733

use positive epsilon for the one test

ff585b5

make test less rigid

d9fe6d4

polish vignette

e751169

add initial values also for auxiliary prior parameters (needed for ho…

bf1771c

…rseshoe prior) to avoid warnings about uninitialized parameters

polish vignette

792b386

danielinteractive assigned mercifr1 Jul 9, 2026

danielinteractive added 4 commits July 9, 2026 20:21

fix linters

b3aa17d

fix docs and spelling

1a3d9a7

fix docs

6bcbbc1

fix snaps

9576e1d

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

450: Add horseshoe prior, as well as constant prior#472

450: Add horseshoe prior, as well as constant prior#472
danielinteractive wants to merge 30 commits into
mainfrom
450-implement-horseshoe

danielinteractive commented Jul 9, 2026

Uh oh!

github-actions Bot commented Jul 9, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Jul 9, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Jul 9, 2026 •

edited

Loading

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

danielinteractive commented Jul 9, 2026

Uh oh!

github-actions Bot commented Jul 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Code Coverage Summary

Diff against main

Uh oh!

github-actions Bot commented Jul 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Unit Tests Summary

Uh oh!

github-actions Bot commented Jul 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Unit Test Performance Difference

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

github-actions Bot commented Jul 9, 2026 •

edited

Loading

github-actions Bot commented Jul 9, 2026 •

edited

Loading

github-actions Bot commented Jul 9, 2026 •

edited

Loading