David Phillippo

174 posts

David Phillippo banner
David Phillippo

David Phillippo

@dmphillippo

@dmphillippo.bsky.social Statistician at University of Bristol | Bayesian, meta-analysis and evidence synthesis, #rstats | Musician and drinker of coffee

Bath, England Katılım Ağustos 2016
266 Takip Edilen387 Takipçiler
Sabitlenmiş Tweet
David Phillippo
David Phillippo@dmphillippo·
📣 New paper! #openaccess Multilevel network meta-regression combines individual patient data and aggregate data in one network, adjusting for differences in effect modifiers between studies, whilst avoiding aggregation bias doi.org/10.1111/rssa.1…
English
3
11
52
0
David Phillippo
David Phillippo@dmphillippo·
No longer posting here - find me where the skies are bluer
English
1
0
4
194
Bang Truong
Bang Truong@bangphd_epi·
@dmphillippo Thanks for the great work of you and your team on this package. When would the baseline risk adjustment be available in ‘multinma’?
English
1
0
0
41
David Phillippo
David Phillippo@dmphillippo·
📣 multinma update v0.7.1 on CRAN * New marginal_effects() function for computing marginal relative effects * Progress bars for long operations * trt_ref argument to predict() has been renamed to baseline_ref for consistency * Bug fixes Full details 👉dmphillippo.github.io/multinma/news/…
David Phillippo tweet media
English
3
6
22
2K
David Phillippo
David Phillippo@dmphillippo·
The marginal_effects() function wraps predict() to create differences or ratios of absolute predictions. For example: * risk differences/ratios from an analysis of log odds ratios * marginal differences in RMST or time-varying marginal hazard ratios from a survival analysis
English
0
1
3
220
David Phillippo
David Phillippo@dmphillippo·
multinma will be back on CRAN as soon as rstan is patched - or sooner if CRAN respond to my emails requesting reinstatement! More details on the memory allocation bug here 👉 github.com/stan-dev/rstan…
English
1
0
1
295
David Phillippo
David Phillippo@dmphillippo·
PSA: multinma is temporarily unavailable from CRAN A small memory allocation bug in Stan tripped some additional CRAN checks, which needs to be patched by rstan. multinma is still fully functional and passes all tests. In the meantime:
English
1
2
6
3.4K
David Phillippo
David Phillippo@dmphillippo·
multinma is back on CRAN 🎉 Stan has been patched to fix the memory allocation bug This release (v0.6.1) also includes a bugfix for piecewise exponential hazards models - changelog here 👉 dmphillippo.github.io/multinma/news/… Binaries will be built by CRAN over the next few days
David Phillippo@dmphillippo

PSA: multinma is temporarily unavailable from CRAN A small memory allocation bug in Stan tripped some additional CRAN checks, which needs to be patched by rstan. multinma is still fully functional and passes all tests. In the meantime:

English
0
1
6
1.6K
David Phillippo
David Phillippo@dmphillippo·
@AbhirupDut9869 Hi Abhirup, CRAN has temporarily archived it due to a small memory allocation bug in stan (beyond my control to fix). Once stan is patched it will be back up 🙂 twitter.com/dmphillippo/st…
David Phillippo@dmphillippo

PSA: multinma is temporarily unavailable from CRAN A small memory allocation bug in Stan tripped some additional CRAN checks, which needs to be patched by rstan. multinma is still fully functional and passes all tests. In the meantime:

English
2
0
0
50
David Phillippo
David Phillippo@dmphillippo·
📣multinma v0.6.0 update on CRAN Major new features (details below): - Survival analysis - Automatic integration convergence checking (faster models!) Plus other improvements and bugfixes Full changelog 👉dmphillippo.github.io/multinma/news/
English
4
6
18
1.8K
David Phillippo
David Phillippo@dmphillippo·
Survival analysis with multilevel network meta-regression? Yes please! New preprint extending ML-NMR to likelihoods of any form, including for survival analysis. Accompanied by a new multinma release v0.6.0, which is on CRAN now. arxiv.org/abs/2401.12640
David Phillippo tweet media
English
2
12
50
5.2K
David Phillippo
David Phillippo@dmphillippo·
Automatic checking of integration error for ML-NMR: - Checks sufficient number of integration points within a single model run - Gives nice warnings if action is required - Much lower default n_int=64 (previously 1000!) means much faster models!
English
0
1
2
134
David Phillippo
David Phillippo@dmphillippo·
More nuggets in this paper: - A new algorithm for automatic convergence checking for numerical integration 👉 fewer integration samples needed, nice warnings, MUCH faster ML-NMR models - M-spline baseline hazard model with a novel random walk shrinkage prior 👀
David Phillippo tweet media
English
0
0
3
188

Keşfet

@bangphd_epi @AbhirupDut9869 @DanielG12754470 @sdias_stats @WeltonNicky @elonmusk @BarackObama @taylorswift13