Changelog
Source:NEWS.md
sdmTMB 0.1.4
Add Pearson residuals for several families.
residuals(fit, type = "pearson")
Useful for checking for overdispersion with N > 1 binomial or Poisson families, among other uses. See theoverdisp_fun()
function at: https://bbolker.github.io/mixedmodelsmisc/glmmFAQ.html#testingforoverdispersioncomputingoverdispersionfactorFix bug when using
residuals()
orsimulate()
with binomial families specified viacbind()
orweights = N
. The binomial sample size wasn’t being passed through typically resulting in Inf/Inf.Add mixture families:
gamma_mix()
,lognormal_mix()
and associated delta/hurdle families:delta_gamma_mix()
,delta_lognormal_mix()
. These families feature a mixture of two distributions with different means but shared variance parameters.Add
delta_beta()
family.
sdmTMB 0.1.3
Tweak
sanity()
checking of standard error size.Export previously experimental
plot_anisotropy()
function. The old function is nowplot_anisotropy2()
.Allow passing offset data through
predict.sdmTMB()
viaoffset
argument.
sdmTMB 0.1.2
Switch
effects = 'ran_vals'
for random intercept values fromtidy.sdmTMB()
to match the broom.mixed package.Make
tidy.sdmTMB()
return a tibble if the tibble package is installed. Note this could affect old code sincedrop = FALSE
is the default for tibbles butdrop = TRUE
is the default for data frames (i.e., tibbles always return a data frame when subsetted).Fix longstanding issue with predicting on newdata with mgcv’s
t2()
. Previously this was disabled because of issues. It now works as expected.Add
knots
argument insdmTMB()
, which is passed to mgcv. A common use would be to specify end points in a cyclical spline (e.g.,s(x, bs = 'cc', k = 4), knots = list(x = c(1, 3, 5, 7))
) when the data don’t extend fully to the boundaries that should match up.
sdmTMB 0.1.1
Preparing for release on CRAN.
Add timevarying AR1 option (originally was always a random walk). See
time_varying_type
argument in?sdmTMB
.Allow prediction on
newdata
with missing time elements. #130Add check for
offset()
(which does not work in sdmTMB, use theoffset
argument instead). #131Add check for random slopes (sdmTMB currently only does random intercepts, although slopes can vary spatially). #131
sdmTMB 0.1.0
ADREPORT several parameters in natural space. https://github.com/pbsassess/sdmTMB/discussions/113
Improve robustness of model
print()
to more esoteric mgcv smoothers.Let
sims_var
work with multiple spatially varying slopes (zeta_s
); return output in named list by coefficients. #107Add
threshold_coefs
tosdmTMB_simulate()
.Don’t make a fake mesh for nonspatial model (faster).
sdmTMB 0.0.26.9001
Add vignettes on visreg, ggeffects, and delta families (thanks J. Indivero!) #83 #87 #89 Forecasting and presenceonly vignettes to be merged in soon.
Add support for emmeans package. See
?emmeans.sdmTMB
for examples.Add support for effects package. The
ggeffects::ggeffect()
function can be used to make fast marginal effects plots.ggeffects::ggpredict()
works with a custom fork of ggeffects. A pull request will be made shortly. #101Add
vcov()
,fixef()
,df.residual
(),formula()
,terms()
, andmodel.frame()
methods.Add support for
"cloglog"
link. Code adapted from glmmTMB for robust likelihood implementation.For delta models, by default share the anisotropy parameters as in VAST. Separate anisotropy (old behavior) can be estimated with
control = sdmTMBcontrol(map = list(ln_H_input = factor(c(1, 2, 3, 4))))
Add experimental
do_index
,predict_args
, andindex_args
insdmTMB()
. These can be used to perform prediction and index calculation at the same time as fitting. For very large datasets or meshes this can save time compared to fitting, predicting, and index calculation in 3 separate steps since the TMB AD object doesn’t have to be rebuilt. This will somewhat slow down the initial fitting.Remove
max_gradient
andbad_eig
fromget_index()
output.Use unique locations on prediction for huge speedups on large
newdata
gridded data.Fix bug where in rare cases
get_index()
would return gibberish small values.Add
bayesian
argument, which whenTRUE
adds Jacobian adjustments for nonlinear transformed parameters. This should beTRUE
if the model will be passed to tmbstan, butFALSE
otherwise. #95Add experimental and notyetexported
sdmTMB:::plot_anisotropy2()
.Add many anisotropy, delta model, and index calculation unit tests.
sdmTMB 0.0.24.9001
Enable random walk random field TMB simulation in
sdmTMB_simulate()
.Add check for irregular time with AR1 or random walk processes.
Fix bugs introduced by delta model code (offsets with
extra_time
and threshold model prediction).Fix bug in
sanity()
message with small random field SDs.
sdmTMB 0.0.24.9000
Add support for ‘delta’ (or ‘hurdle’) models. See examples and documentation in
?sdmTMB
. This has resulted in a substantial restructuring of the internal model code. By default both model components (e.g., binomial & Gamma) share the same formula, spatial, and spatiotemporal structure, but these can be separated by supplying argument values in lists where the first element corresponds to the first model and the second element corresponds to the second model (with some limitations as described in?sdmTMB
documentation ‘Details’).Add support for multiple spatially varying coefficients (used to be limited to a single variable).
Add compatibility with the ‘visreg’ package for visualizing conditional effects of parameters. See
?visreg_delta
for examples.Add MCMC residual type to
residuals.sdmTMB()
. These are a ‘better’ residuals but slower to calculate. See documentation ‘Details’ in?residuals.sdmTMB
.Make
offset
an argument insdmTMB()
. Using the reserved wordoffset
in the formula is now deprecated.Add
sanity()
function to perform some basic sanity checks on model fits.Make an
sdmTMB()
model object compatible withupdate()
method.Remove several deprecated arguments.
Overhaul examples in
?sdmTMB
.Use faster “lowrank sparse hessian biascorrection” TMB bias correction.
Add parallel processing support. See
parallel
argument insdmTMBcontrol
. By default, grabs value ofsdmTMB.cores
option. E.g.options(sdmTMB.cores = 4)
. Only currently enabled on Mac/Linux. Using too many cores can be much slower than 1 core.Use ‘cli’ package
cli_abort()
/cli_warn()
/cli_inform()
overstop()
/warning()
/message()
.Add many unit tests.
sdmTMB 0.0.23.9000
 A package version number that was used for internal testing in the ‘delta’ branch by several people.
sdmTMB 0.0.22.9000
 Fix bug in predictions with
poly(..., raw = FALSE)
on newdata. #77
sdmTMB 0.0.21.9009
Add experimental
sdmTMB_stacking()
for ensemble model stacking weights.Add fake mesh if random fields are all off. #59
Make
predict(..., newdata = NULL)
also uselast.par.best
instead oflast.par
to matchnewdata = df
.Fix bug in MVN fixedeffect prior indexing
sims
andn_sims
arguments have been deprecated and standardized tonsim
to match thesimulate()
S3 method.Bias correction on
get_index()
andget_cog()
is now selective and is just applied to the necessary derived parameters.INLA projection matrix ‘A’ is now shared across spatial and spatiotemporal fields.
Add
add_utm_columns()
to ease adding UTM columns.
sdmTMB 0.0.20.9001
Add
dharma_residuals()
.Fix bug in
simulate.sdmTMB()
andresiduals.sdmTMB()
for binomial family.
sdmTMB 0.0.20.9000
Smoothers now appear in
print()
output. The format should roughly match brms. The maineffect component (e.g.,sdepth
fors(depth)
) represents the linear component and the random effect (e.g.,sds(depth)
) component in the output corresponds to the standard deviation of the penalized weights.Add
censored_poisson(link = 'log')
family; implemented by @joenomiddlenamefields
insdmTMB()
is now deprecated and replaced byspatiotemporal
.include_spatial
insdmTMB()
is now deprecated and replaced byspatial
.spatial_only
insdmTMB()
is now deprecated and replaced byspatiotemporal
. E.g.spatial_only = TRUE
is nowspatiotemporal = 'off'
or leavingtime = NULL
.spde
insdmTMB()
is now deprecated and replaced bymesh
.sdmTMB_simulate()
is new and will likely replacesdmTMB_sim()
eventually.sdmTMB_simulate()
is set up to take a formula and a data frame and is easier to use if you want different spatial observations (and covariates) for each time slice. It can also take a fitted model and modify parts of it to simulate. Finally, this function uses TMB for simulation and so is much faster and more flexible in what it can simulate (e.g., anisotropy) than the previous version.spatial_trend
is nowspatial_varying
and accepts a onesided formula with a single predictor of any coefficient that should varying in space as a random field. Note that you may want to include a fixed effect for the same variable to improve interpretability. If the (scaled) time column is used, it will represent a localtimetrend model as before.The Tweedie power (p) parameter is now in
print()
andtidy()
output.thetaf
is nowtweedie_p
insdmTMB_sim()
.
sdmTMB 0.0.19.9002
 Simulation from the parameter covariance matrix works if random effects are turned off. #57
sdmTMB 0.0.19.9000
 Smoothers
s()
are now penalized smoothers: they determine the degree of wiggliness (as in mgcv) and it is no longer necessary to choose an appropriatek
value a priori. Models fit with previous versions of sdmTMB withs(x, k = ...)
will not match models specified the same way in version >= 0.0.19 since the basis functions are now penalized. All the variousmgcv::s()
options should be supported butt2()
(andti()
andte()
) are not supported.
sdmTMB 0.0.18.9001
Add ELPD (expected log predictive density) to
sdmTMB_cv()
https://arxiv.org/abs/1507.04544Fix bug evaluating
...
whensdmTMB_cv()
was called within a function. #54
sdmTMB 0.0.17.9000
Add random walk option:
fields = "RW"
.Depreciate
ar1_fields
argument. See newfields
argument in `sdmTMB().Many packages moved from ‘Imports’ to ‘Suggests’
sdmTMB 0.0.16.9000
Lower default
nlminb()
eval.max
anditer.max
to 1000 and 2000.Added
profile
option insdmTMBcontrol()
. This can dramatically improve model fitting speed with many fixed effects. Note the result is likely to be slightly different withTRUE
vs.FALSE
.Added simulation from the MVN precision matrix to
predict.sdmTMB()
. See thesims
argument.Added
gather_sims()
andspread_sims()
to extract parameter simulations from the joint precision matrix in a format that matches the tidybayes package.Added
get_index_sims()
for a population index calculated from the MVN simulation draws.Added
extract_mcmc()
to extract MCMC samples if the model is passed to tmbstan.Added the ability to predict from a model fitted with tmbstan. See the
tmbstan_model
argument inpredict.sdmTMB()
.Allowed for separate random field Matern range parameters for spatial and spatiotemporal fields. E.g.
sdmTMB(shared_range = FALSE)
Bounded the AR1 rho parameter between 0.999 and 0.999 to improve convergence; was 1 to 1. Please post an issue if this creates problems for your model.
Added
map
,start
,lower
, andupper
options to control model fitting. SeesdmTMBcontrol()
.Added priors for all parameters. See
?sdmTMB::priors
and thepriors
argument insdmTMB()
. PC priors are available for the random fields. See?pc_matern
and the details there.Moved many lesscommon arguments from
sdmTMB()
tosdmTMBcontrol()
.Fix bug in
sdmTMB_cv()
where fitting and testing data splits were reversed. I.e., the small chunk was fit; the big chunk was tested.
sdmTMB 0.0.15.9000
Added experimental penalized complexity (PC) prior as used in INLA. See arguments
matern_prior_O
andmatern_prior_E
.Added back
normalize
argument tosdmTMB()
and default toFALSE
. Setting toTRUE
can dramatically speed up some model fits (~4 times for some test models).
sdmTMB 0.0.14.9001
 Added some protections for possible user errors:
 AR1 with a spatialonly model
 Missing factor levels in time
 Coordinate systems that are too big
sdmTMB 0.0.14.9000
Add
re_form_iid
topredict.sdmTMB()
.Add
map_rf
option tosdmTMB()
. This lets you map (fix at their starting values of zero) all random fields to produce a classic GLM/GLMM.
sdmTMB 0.0.13.9000
 Add IID random intercepts interface. E.g.
... + (1  g)
#34
sdmTMB 0.0.12.9000
 Add
epsilon_predictor
argument insdmTMB()
to allow a model of the spatiotemporal variance through time.
sdmTMB 0.0.10.9000
Fixed parameter initialization for inverse links #35
Switched Gamma ‘phi’ parameter to representing shape instead of CV to match glm(), glmmTMB(), etc.
sdmTMB 0.0.9.9000
 Switched the density/abundance index calculation to use the link function as opposed to a hardcoded log() so that the
get_generic()
function can be used to grab things like standardized average values of the response across a grid. What used to belog_total
in the raw TMB output is nowlink_total
but most users you shouldn’t notice any difference.
sdmTMB 0.0.8.9000
Overhauled the simulation function. The function is now called
sdmTMB_sim()
and uses INLA functions instead of RandomFields functions for simulating the random fields.The simulation function can now accommodate all families and links and takes an INLA mesh as input.
sdmTMB 0.0.7.9001
 Allow specifying degrees of freedom in the Studentt family #29
sdmTMB 0.0.7.9000
Added a
tidy()
method (from broom and broom.mixed) to return a data frame of parameter estimates. The function can extract the fixed effects or the random effect parameters (variances, AR1 correlation, spatial range).Added an argument
extra_time
tosdmTMB()
. This introduces additional time slices that you can then predict on if you want to interpolate or forecast. Internally, it uses Eric Ward’s ‘weights hack’. This is also useful if you have data unevenly spaced in time and you want the gaps evenly spaced for a random walk or AR1 process (add any missing years toextra_time
).make_spde()
is now replaced withmake_mesh()
andmake_spde()
has been soft deprecated.make_mesh()
carries through the x and y column names to the predict function and is more in line with the tidyverse style of taking a data frame first.make_mesh()
can acceptcutoff
as an argument (as in INLA), which is likely a better default way to specify the mesh since it scales across regions better and is line with the literature on INLA.make_mesh()
can use a binary search algorithm to find a cutoff that best matches a desired number of knots (thanks to Kelli Johnson for the idea).Barrier meshes are now possible. See
add_barrier_mesh()
for an example.There is a pkgdown website now that gets auto generated with GitHub actions.
There is the start of a model description vignette. It is very much a work in progress.
sdmTMB 0.0.6.9005
 Fixed bug in predictions with standard errors where one(?) parameter (a breakpoint parameter) would be passed in at its initial instead of MLE value.
sdmTMB 0.0.6.9004
Fixed bug with predictions on new data in models with break points

Overhauled cross validation function. The function now:
 uses Eric’s weights hack so it can also be used for forecasting
 initializes subsequent folds at the MLE of the first fold for considerable speed increases
 works in parallel if a future plan initialized; see examples
Added threshold parameters to the print method
Added forecasting example with the weights hack
Fixed bug in linear break point models
sdmTMB 0.0.6.9002
Fixed GAM predictions with all 0s in new data.
Add linear and logistic threshold models. #17
sdmTMB 0.0.5.9000
Added parsing of mgcv formulas for splines. #16
Added ability to predict with standard errors at the population level. This helps with making marginaleffect plots. #15
Added optimization options to aid convergence. Also added
run_extra_optimization()
to run these on already fit models. Default is for no extra optimization.Added binomial likelihood to cross validation. Git hash
ee3f3ba
.Started keeping track of news in
NEWS.md
.