Changelog
Source:NEWS.md
multinma 0.7.2
CRAN release: 2024-09-16
- Fix: Predictions for non-proportional hazards IPD NMA or ML-NMR survival models using
aux_regression = ~.trt
were incorrectly omitting the treatment effects on the auxiliary parameter(s) in some cases (#43). - Fix: Calling
marginal_effects()
for survival outcomes with a single target population previously gave an error. - Fix: Predictions from exponential models where
aux_regression
had been specified were giving an error (#44).aux_regression
andaux_by
have no effect for exponential models since there are no auxiliary (shape) parameters and are ignored, now with a warning. - Fix: Avoid an error when trying to fit M-spline models combining IPD and AgD in R versions prior to 4.1.0, due to integer coercion of factors by
c()
.
multinma 0.7.0
CRAN release: 2024-05-07
- Feature: The new
marginal_effects()
function produces marginal treatment effects, as a wrapper around absolute predictions frompredict()
. For example, for an analysis with a binary outcome marginal odds ratios, risk ratios, or risk differences may be produced. For survival outcomes, marginal effects may be based on the full range of predictions produced bypredict()
, such as marginal differences in restricted mean survival times, or time-varying marginal hazard ratios. - Feature: Progress bars are now displayed when running interactively for calculations with
predict()
ormarginal_effects()
from ML-NMR models that may take longer to run. These can be controlled with the newprogress
argument. - Deprecation: The
trt_ref
argument topredict()
has been renamed tobaseline_ref
; usingtrt_ref
is now soft-deprecated. Renaming this argumentbaseline_ref
follows the naming convention for the other arguments (baseline_type
,baseline_level
) that specify the details of a providedbaseline
distribution. This also makes way for the newmarginal_effects()
functionality. - Fix: Fallback formatting used by print methods when the crayon package is not installed now works properly, rather than giving errors.
- Fix: Small bug caused
predict()
for AgD meta-regression models with new data andbaseline_type = "response"
to fail with an error. - Fix: The number of studies on a contrast in a network plot
plot.nma_data()
withweight_edges = TRUE
was incorrect when a study had multiple arms of the same treatment. This now correctly counts the number of studies making a comparison, rather than the number of arms.
multinma 0.6.1
CRAN release: 2024-03-06
- Fix: Piecewise exponential hazard models no longer give errors during set-up. Calculation of RW1 prior weights needed to be handled as a special case.
multinma 0.6.0
CRAN release: 2024-01-24
Feature: Survival/time-to-event models are now supported
-
set_ipd()
now has aSurv
argument for specifying survival outcomes usingsurvival::Surv()
, and a new functionset_agd_surv()
sets up aggregate data in the form of event/censoring times (e.g. from digitized Kaplan-Meier curves) and overall covariate summaries. - Left, right, and interval censoring as well as left truncation (delayed entry) are all supported.
- The available likelihoods are Exponential (PH and AFT forms), Weibull (PH and AFT forms), Gompertz, log-Normal, log-Logistic, Gamma, Generalised Gamma, flexible M-splines on the baseline hazard, and piecewise exponential hazards.
- Auxiliary parameters (e.g. shapes, spline coefficients) are always stratified by study to respect randomisation, and may be further stratified by treatment (e.g. to relax the proportional hazards assumption) and/or by additional factors using the
aux_by
argument tonma()
. - A regression model may be defined for the auxiliary parameters using the
aux_regression
argument tonma()
, allowing non-proportionality to be modelled by treatment and/or covariate effects on the shapes or spline coefficients. - The
predict()
method produces estimates of survival probabilities, hazards, cumulative hazards, mean survival times, restricted mean survival times, quantiles of the survival time distribution, and median survival times. All of these predictions can be plotted using theplot()
method. - The
geom_km()
function assists in plotting Kaplan-Meier curves from a network object, for example to overlay these on estimated survival curves. Thetransform
argument can be used to produce log-log plots for assessing the proportional hazards assumption, along with cumulative hazards or log survival curves. - A new vignette demonstrates ML-NMR survival analysis with an example of progression-free survival after autologous stem cell transplant for newly diagnosed multiple myeloma, with corresponding datasets
ndmm_ipd
,ndmm_agd
, andndmm_agd_covs
.
Feature: Automatic checking of numerical integration for ML-NMR models
- The accuracy of numerical integration for ML-NMR models can now be checked automatically, and is by default. To do so, half of the chains are run with
n_int
and half withn_int/2
integration points. Any Rhat or effective sample size warnings can then be ascribed to either: non-convergence of the MCMC chains, requiring increased number of iterationsiter
innma()
, or; insufficient accuracy of numerical integration, requiring increased number of integration pointsn_int
inadd_integration()
. Descriptive warning messages indicate which is the case. - This feature is controlled by a new
int_check
argument tonma()
, which is enabled (TRUE
) by default. - Saving thinned cumulative integration points can now be disabled with
int_thin = 0
, and is now disabled by default. The previous default wasint_thin = max(n_int %/% 10, 1)
. - Because we can now check sufficient accuracy automatically, the default number of integration points
n_int
inadd_integration()
has been lowered to 64. This is still a conservative choice, and will be sufficient in many cases; the previous default of 1000 was excessive. - As a result, ML-NMR models are now much faster to run by default, both due to lower
n_int
and disabling saving cumulative integration points.
Other updates
- Feature:
dic()
now includes an option to use the pV penalty instead of pD. - Feature: The
baseline
andaux
arguments topredict()
can now be specified as the name of a study in the network, to use the parameter estimates from that study for prediction. - Improvement:
predict()
will now produce aggregate-level predictions over a sample of individuals innewdata
for ML-NMR models (previouslynewdata
had to include integration points). - Improvement: Compatibility with future rstan versions (PR #25).
- Improvement: Added a
plot.mcmc_array()
method, as a shortcut forplot(summary(x), ...)
. - Fix: In
plot.nma_data()
, using a customlayout
that is not a string (e.g. a data frame of layout coordinates) now works as expected whennudge > 0
. - Fix: Documentation corrections (PR #24).
- Fix: Added missing
as.tibble.stan_nma()
andas_tibble.stan_nma()
methods, to complement the existingas.data.frame.stan_nma()
. - Fix: Bug in ordered multinomial models where data in studies with missing categories could be assigned the wrong category (#28).
multinma 0.5.1
CRAN release: 2023-05-24
- Fix: Now compatible with latest StanHeaders v2.26.25 (fixes #23)
- Fix: Dealt with various tidyverse deprecations
- Fix: Updated TSD URLs again (thanks to @ndunnewind)
multinma 0.5.0
CRAN release: 2022-08-29
- Feature: Treatment labels in network plots can now be nudged away from the nodes when
weight_nodes = TRUE
, using the newnudge
argument toplot.nma_data()
(#15). - Feature: The data frame returned by calling
as_tibble()
oras.data.frame()
on annma_summary
object (such as relative effects or predictions) now includes columns for the corresponding treatment (.trt
) or contrast (.trta
and.trtb
), and a.category
column may be included for multinomial models. Previously these details were only present as part of theparameter
column - Feature: Added log t prior distribution
log_student_t()
, which can be used for positive-valued parameters (e.g. heterogeneity variance). - Improvement:
set_agd_contrast()
now produces an informative error message when the covariance matrix implied by these
column is not positive definite. Previously this was only checked by Stan after calling thenma()
function. - Improvement: Updated plaque psoriasis ML-NMR vignette to include new analyses, including assessing the assumptions of population adjustment and synthesising multinomial outcomes.
- Improvement: Improved behaviour of the
.trtclass
special in regression formulas, now main effects of.trtclass
are always removed since these are collinear with.trt
. This allows expansion of interactions with*
to work properly, e.g.~variable*.trtclass
, whereas previously this resulted in an over-parametrised model. - Fix: CRAN check note for manual HTML5 compatibility.
- Fix: Residual deviance and log likelihood parameters are now named correctly when only contrast-based aggregate data is present (PR #19).
multinma 0.4.2
CRAN release: 2022-03-02
- Fix: Error in
get_nodesplits()
when studies have multiple arms of the same treatment. - Fix:
print.nma_data()
now prints the repeated arms when studies have multiple arms of the same treatment. - Fix: CRAN warning regarding invalid img tag height attribute in documentation.
multinma 0.4.0
CRAN release: 2022-01-18
- Feature: Node-splitting models for assessing inconsistency are now available with
consistency = "nodesplit"
innma()
. Comparisons to split can be chosen using thenodesplit
argument, by default all possibly inconsistent comparisons are chosen usingget_nodesplits()
. Node-splitting results can be summarised withsummary.nma_nodesplit()
and plotted withplot.nodesplit_summary()
. - Feature: The correlation matrix for generating integration points with
add_integration()
for ML-NMR models is now adjusted to the underlying Gaussian copula, so that the output correlations of the integration points better match the requested input correlations. A new argumentcor_adjust
controls this behaviour, with options"spearman"
,"pearson"
, or"none"
. Although these correlations typically have little impact on the results, for strict reproducibility the old behaviour from version 0.3.0 and below is available withcor_adjust = "legacy"
. - Feature: For random effects models, the predictive distribution of relative/absolute effects in a new study can now be obtained in
relative_effects()
andpredict.stan_nma()
respectively, using the new argumentpredictive_distribution = TRUE
. - Feature: Added option to calculate SUCRA values when summarising the posterior treatment ranks with
posterior_ranks()
orposterior_rank_probs()
, when argumentsucra = TRUE
. - Improvement: Factor order is now respected when
trt
,study
, ortrt_class
are factors, previously the order of levels was reset into natural sort order. - Improvement: Update package website to Bootstrap 5 with release of pkgdown 2.0.0
- Fix: Model fitting is now robust to non-default settings of
options("contrasts")
. - Fix:
plot.nma_data()
no longer gives a ggplot deprecation warning (PR #6). - Fix: Bug in
predict.stan_nma()
with a single covariate whennewdata
is adata.frame
(PR #7). - Fix: Attempting to call
predict.stan_nma()
on a regression model with only contrast data and nonewdata
orbaseline
specified now throws a descriptive error message.
multinma 0.3.0
CRAN release: 2021-03-18
- Feature: Added
baseline_type
andbaseline_level
arguments topredict.stan_nma()
, which allow baseline distributions to be specified on the response or linear predictor scale, and at the individual or aggregate level. - Feature: The
baseline
argument topredict.stan_nma()
can now accept a (named) list of baseline distributions ifnewdata
contains multiple studies. - Improvement: Misspecified
newdata
arguments to functions likerelative_effects()
andpredict.stan_nma()
now give more informative error messages. - Fix: Constructing models with contrast-based data previously gave errors in some scenarios (ML-NMR models, UME models, and in some cases AgD meta-regression models).
- Fix: Ensure CRAN additional checks with
--run-donttest
run correctly.
multinma 0.2.1
CRAN release: 2021-01-09
- Fix: Producing relative effect estimates for all contrasts using
relative_effects()
withall_contrasts = TRUE
no longer gives an error for regression models. - Fix: Specifying the covariate correlation matrix
cor
inadd_integration()
is not required when only one covariate is present. - Improvement: Added more detailed documentation on the likelihoods and link functions available for each data type (
likelihood
andlink
arguments innma()
).
multinma 0.2.0
CRAN release: 2020-12-04
- Feature: The
set_*()
functions now acceptdplyr::mutate()
style semantics, allowing inline variable transformations. - Feature: Added ordered multinomial models, with helper function
multi()
for specifying the outcomes. Accompanied by a new data sethta_psoriasis
and vignette. - Feature: Implicit flat priors can now be specified, on any parameter, using
flat()
. - Improvement:
as.array.stan_nma()
is now much more efficient, meaning that many post-estimation functions are also now much more efficient. - Improvement:
plot.nma_dic()
is now more efficient, particularly with large numbers of data points. - Improvement: The layering of points when producing “dev-dev” plots using
plot.nma_dic()
with multiple data types has been reversed for improved clarity (now AgD over the top of IPD). - Improvement: Aggregate-level predictions with
predict()
from ML-NMR / IPD regression models are now calculated in a much more memory-efficient manner. - Improvement: Added an overview of examples given in the vignettes.
- Improvement: Network plots with
weight_edges = TRUE
no longer produce legends with non-integer values for the number of studies. - Fix:
plot.nma_dic()
no longer gives an error when attempting to specify.width
argument when producing “dev-dev” plots.
multinma 0.1.1
- Reduced size of vignettes
- Added methods paper reference to DESCRIPTION
- Added zenodo DOI
multinma 0.1.0
- Feature: Network plots, using a
plot()
method fornma_data
objects. - Feature:
as.igraph()
,as_tbl_graph()
methods fornma_data
objects. - Feature: Produce relative effect estimates with
relative_effects()
, posterior ranks withposterior_ranks()
, and posterior rank probabilities withposterior_rank_probs()
. These will be study-specific when a regression model is given. - Feature: Produce predictions of absolute effects with a
predict()
method forstan_nma
objects. - Feature: Plots of relative effects, ranks, predictions, and parameter estimates via
plot.nma_summary()
. - Feature: Optional
sample_size
argument forset_agd_*()
that:- Enables centering of predictors (
center = TRUE
) innma()
when a regression model is given, replacing theagd_sample_size
argument ofnma()
- Enables production of study-specific relative effects, rank probabilities, etc. for studies in the network when a regression model is given
- Allows nodes in network plots to be weighted by sample size
- Enables centering of predictors (
- Feature: Plots of residual deviance contributions for a model and “dev-dev” plots comparing residual deviance contributions between two models, using a
plot()
method fornma_dic
objects produced bydic()
. - Feature: Complementary log-log (cloglog) link function
link = "cloglog"
for binomial likelihoods. - Feature: Option to specify priors for heterogeneity on the standard deviation, variance, or precision, with argument
prior_het_type
. - Feature: Added log-Normal prior distribution.
- Feature: Plots of prior distributions vs. posterior distributions with
plot_prior_posterior()
. - Feature: Pairs plot method
pairs()
. - Feature: Added vignettes with example analyses from the NICE TSDs and more.
- Fix: Random effects models with even moderate numbers of studies could be very slow. These now run much more quickly, using a sparse representation of the RE correlation matrix which is automatically enabled for sparsity above 90% (roughly equivalent to 10 or more studies).