Remove dependency to rgho. get_who_mr is still locally
working
heemod 1.0.0
Breaking changes
dplyr’s pipe now causes an error when chaining survival operation.
The new pipe |> is required in this situation.
define_survival() has been renamed
define_surv_dist() for naming consistency
It is now necessary to use define_surv_fit() to specify
a survival fit created with survfit(),
flexsurvreg() or flexsurvspline()
New Features
It is now possible to run probabilistic sensitivity analysis (PSA)
with survival objects - either created from a parametric distribution
(with define_surv_dist) or with real data fitted with
survfit() or flexsurvreg(). See
vignette("j-survival_2_psa")
plot.surv_object() gains psa argument
allowing to plot the distribution to check for its variability.
Created method c.uneval_parameters() to combine outputs
of define_parameters().
Other changes
All operation functions on survival objects are now of class
surv_object
heemod 0.16.0
Remove lazyeval, plyr and pryr dependency
For PSM, when OS is lower to PFS, force the transition probability
to be 0 (#7 @william-rawlinson)
get_who_mr() is working again
Mortality rates gathered with
get_who_mr(..., local = TRUE) are only available as
pooled for high income countries.
prop, multinom and
make_gamma, deprecated since a long time are now
unavailable, to be replaced with binomial,
multinomial and gamma, respectively.
markov_cycle is now deprecated in favor of
model_time and state_cycle in favor of
state_time
heemod 0.15.1
Compliance with r-devel
heemod 0.15.0
Performance improvements: using state_time is much faster now, as
well as probabilistic sensitivity analyses
heemod 0.14.5
Rebuild vignettes
fix guides( = FALSE)
heemod 0.14.4
updates for compatibility with rlang 1.0.0
heemod 0.14.2
checks cairo_pdf availability
heemod 0.14.0
Breaking changes
argument “method” for run_model was inverted. Now “beginning”
overestimates costs and “end” underestimates costs (#345 @zaddyzad)
heemod 0.13.0
Prepare for dplyr 1.0.0
Bugfixes
Fix problem with state_time (fix #343 @Reale3)
heemod 0.12.0
Bugfixes
Ready for tibble 3.0
look_up() displays a more informative message when
searching several values at once
heemod 0.11.0
Backend changes
States are now length 2 lists:
.dots: the state values
starting_values: the state values when entering the state
Compatibility with dplyr 0.8: replaced all underscored (SE) versions
of all verbs
Bugfixes
get_who_mr() is again able to fetch data from GHO
server
heemod 0.10.0
New features
define_state() gains the starting_values
argument (same as define_strategy()).
heemod 0.9.4
Compatibility with dplyr v0.8
heemod 0.9.3
Backend changes
Remove Hmisc dependency for weighted summaries.
heemod 0.9.2
Breaking changes
Survival function renamed:
pool()=>mix().
New features
Starting values with define_starting_values().
Check for comma as a decimal separator in tabular data.
Auto-re-indent transition matrices with
reindent_transition().
use_distribution() to re-sample from empirical data
(e.g. MCMC fit posterior distribution).
Bugfixes
Better error-checking in multinomial parameters definition.
Cleaner define_psa() back-end code, variables can now
be used to define distribution parameters.
Handle cases when parameters depend on state_time but
those parameters are not used by a strategy.
Empty calls to modify() are supported.
Fix error in survival vignette.
Backend changes
The development branch is now called master, the
release branch is called cran.
Survival operation are wrapped in a common class.
Expansion code moved to own function.
Faster computation of expanded states.
Stricter dependency version management (to avoid install failures on
an outdated system).
Removed dependency to tidyr.
heemod 0.9.1
Breaking changes
Survival function renamed:
project()=>join().
Removed get_code().
New features
NMB is now reported as relative values.
Bugfixes
Fixed error with run_dsa() in state expansion
situations.
Backend changes
Multiple changes to prepare for the dplyr update
0.6.0.
heemod 0.9.0
heemod can now be cited with:
Filipovic-Pierucci A, Zarca K and Durand-Zaleski I (2017). “Markov
Models for Health Economic Evaluations: The R Package heemod.” ArXiv
e-prints. R package version 0.8.0, 1702.03252
Model calibration with calibrate_model().
init and inflow can refer to values from
define_parameters(), and are thus accessible to PSA /
DSA.
inflow can be time-varying.
Breaking changes
get_probs_from_surv()=>compute_surv().
New features
Operations on survival functions, see
vignette("j-survival"). Thanks to Jordan Amdahl.
Model calibration with calibrate_model(). Thanks to Matthew Wiener.
State membership correction works for partitioned survival
model.
Custom state membership correction functions can be passed to the
method argument of run_model().
get_who__mr() can take a region argument,
and automatically pool results when sex is not passed.
Additional DSA plotting options.
Bugfixes
heemod::discount() now produces results similar to
discount().
Backend changes
Renamed memoised functions.
NSE aliases (*_) to survival operation functions.
heemod 0.8.0
Breaking changes
strategy becomes a reserved parameter name.
Counting method "half-cycle" is deprecated.
resample argument in run_psa() renamed to
psa.
Probability distributions for PSA were renamed, see
?distributions.
state_cycle renamed to state_time, added a
model_time alias to model_time.
The inflow argument for budget impact analysis is
specified with define_inflow().
prob_to_prob()=>rescale_prob().
New features
Transition probabilities from survival models with
get_probs_from_surv():
Parametrically defined by define_survival().
Or fitted on data by the flexsurv package.
Support for partitioned survival models with
define_part_surv().
Plot EVPI.
Export PSA files for Sheffield Accelerated Value of Information
software.
Individuals can enter the model after the beginning with the
inflow argument in run_model() (mainly for
budget impact analysis).
Strategy name can be used to define values with
dispatch_strategy() or using the strategy name
(vignettes homogeneous and probabilistic have been
updated to use this feature).
Beta and triangle distributions for PSA.
Custom distributions can be defined.
Co-variance analysis on strategy differences, more options for
gam() fitting.
Other features
Convenience function rescale_discount_rate().
Better error messages at parameter evaluation.
combine_probs(): given several independent
probabilities of an event, return the total probability of the
event.
More informative error messages for incorrect matrices.
Infinite parameter values generate an error.
New parameters can be added with modify().
Backend changes
Cleaner handling of clusters.
Package diagram, Hmisc and
logitnorm moved from Imports to
Suggests.
Bugfixes
Fixed several bugs that would return incorrect efficiency frontiers
in some situations, or would return duplicated strategy names in some
edge cases (thanks to Vince
Daniels).
Fixed a failure of tabular input when a column could be read as all
numeric.
Character variables from newdata were mistakenly parsed
as lazy expressions.
newdata now handles factor variables.
state_cycle_limit was not passed to PSA, DSA, or
updating.
PSA and DSA tabular files were not saved.
Acknowledgments
Thanks to Matthew
Wiener, especially for the survival analysis code.
heemod 0.7.1
Bugfixes
Fixed an error resulting in incorrect co-variance analysis results
when relations between values and parameters were negative.
heemod 0.7.0
Breaking changes
Some plotting arguments changed
(e.g. type=>results).
New features
Added co-variance analysis for PSA with type = "cov"
plot.
All plotting functions can now represent multiple strategies with
facets.
CECA plotted on a log scale by default.
Black & white plots for publications with the bw
plot option.
Remove variables that are not sensitive in DSA with
remove_ns.
Backend changes
Important object structure change (from attributes to lists).
More systematic use of getter functions.
More standardized processing of model objects.
Unit tests rely less on printed results.
Using new nomenclature in back-end functions
(model=>strategy).
base_strategy divided in 3 concepts:
central_strategy, root_strategy,
noncomparable_strategy.
Non-heemod versions of discount() throw warnings.
heemod 0.6.0
Breaking changes
Base model cannot be specified anymore: it is always the least
costly model.
Renamed argument transition_matrix =>
transition in define_strategy().