[Pomp-commits] r903 - in pkg/pomp: . inst man
noreply at r-forge.r-project.org
noreply at r-forge.r-project.org
Fri Mar 21 16:46:30 CET 2014
Author: kingaa
Date: 2014-03-21 16:46:30 +0100 (Fri, 21 Mar 2014)
New Revision: 903
Added:
pkg/pomp/inst/NEWS.Rd
Modified:
pkg/pomp/DESCRIPTION
pkg/pomp/inst/NEWS
pkg/pomp/man/pomp.Rd
Log:
- remove some outdated remarks in 'pomp' man page
- put NEWS into Rd format
Modified: pkg/pomp/DESCRIPTION
===================================================================
--- pkg/pomp/DESCRIPTION 2014-03-21 15:32:17 UTC (rev 902)
+++ pkg/pomp/DESCRIPTION 2014-03-21 15:46:30 UTC (rev 903)
@@ -2,7 +2,7 @@
Type: Package
Title: Statistical inference for partially observed Markov processes
Version: 0.49-1
-Date: 2014-03-20
+Date: 2014-03-21
Authors at R: c(person(given=c("Aaron","A."),family="King",
role=c("aut","cre"),email="kingaa at umich.edu"),
person(given=c("Edward","L."),family="Ionides",role=c("aut")),
Modified: pkg/pomp/inst/NEWS
===================================================================
--- pkg/pomp/inst/NEWS 2014-03-21 15:32:17 UTC (rev 902)
+++ pkg/pomp/inst/NEWS 2014-03-21 15:46:30 UTC (rev 903)
@@ -1,566 +1,927 @@
-NEWS
-0.49-1
- o A new method, 'probe.match.objfun', constructs objective functions suitable for use in optimizers.
+_N_e_w_s _f_o_r _P_a_c_k_a_g_e '_p_o_m_p'
- o 'pomp' now depends on 'nloptr', which provides a suite of optimization algorithms.
- This package can now be used in various methods for optimization of an objective function.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_9-_1:
- o New inline C functions 'to_log_barycentric' and 'from_log_barycentric' are provided in 'pomp.h' to facilitate log-barycentric transformations.
- These have proven very useful in dealing with parameters constrained to sum to one (e.g., initial conditions of compartmental models).
+ • A new method, 'probe.match.objfun', constructs objective
+ functions suitable for use in optimizers.
-0.48-3
- o Correct a bug in 'abc' to do with parameter transformation.
+ • 'pomp' now depends on 'nloptr', which provides a suite of
+ optimization algorithms. This package can now be used in
+ various methods for optimization of an objective function.
-0.48-1
- o Create new 'dprior' and 'rprior' slots for 'pomp' objects.
- These will be used by the Bayesian methods (currently 'abc', 'bsmc', and 'pmcmc').
- The 'hyperparams' argument to these methods has been removed;
- hyperparameters are now treated just as any others.
+ • New inline C functions 'to_log_barycentric' and
+ 'from_log_barycentric' are provided in 'pomp.h' to facilitate
+ log-barycentric transformations. These have proven very
+ useful in dealing with parameters constrained to sum to one
+ (e.g., initial conditions of compartmental models).
- o 'bsmc' can now be called so that the particles are drawn from the prior distribution (as set by the 'rpior' slot).
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_8-_3:
- o Some of the longer tests will only be run if an environment variable is set.
+ • Correct a bug in 'abc' to do with parameter transformation.
-0.47-4
- o Revisit 'dacca' bug. Set negative compartments to zero along with compartments immediately downstream.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_8-_1:
-0.47-3
- o Fix bug that arises only very occasionally in the 'dacca' cholera example.
+ • Create new 'dprior' and 'rprior' slots for 'pomp' objects.
+ These will be used by the Bayesian methods (currently 'abc',
+ 'bsmc', and 'pmcmc'). The 'hyperparams' argument to these
+ methods has been removed; hyperparameters are now treated
+ just as any others.
- o Modify 'dacca' model so that rare positivity violations are punished in a different way.
- This modifies the formal model slightly.
+ • 'bsmc' can now be called so that the particles are drawn from
+ the prior distribution (as set by the 'rpior' slot).
-0.47-2
- o By default, 'pompBuilder' now creates all files in the temporary directory.
+ • Some of the longer tests will only be run if an environment
+ variable is set.
-0.47-1
- o 'abc' implements Approximate Bayesian Computation for pomp models.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_7-_4:
-0.46-1
- o 'pompExample' now has an optional argument, 'envir', determining which environment the pomp object will be loaded into.
+ • Revisit 'dacca' bug. Set negative compartments to zero along
+ with compartments immediately downstream.
- o 'logmeanexp' now has an optional argument, 'se', allowing for computation of an approximate standard error.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_7-_3:
-0.45-8
- o bug fix in 'gompertz' example.
+ • Fix bug that arises only very occasionally in the 'dacca'
+ cholera example.
-0.45-7
- o bug fix in 'pmcmc': Metropolis-Hastings ratio was incorrect except for flat priors!
-
-0.45-6
- o a fix so that 'pompBuilder' will find 'pomp.h' header file on Windows machines. Thanks to Dave Hayman for finding the problem.
+ • Modify 'dacca' model so that rare positivity violations are
+ punished in a different way. This modifies the formal model
+ slightly.
- o new 'logmeanexp' function.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_7-_2:
- o some reorganization of the source package structure.
+ • By default, 'pompBuilder' now creates all files in the
+ temporary directory.
-0.45-4
- o changes in the way 'reulermultinom', 'deulermultinom', 'dot_product' are exported to other packages. Rather than just being exported as linkables, these are now also defined as static inline functions in the 'pomp.h' header.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_7-_1:
-0.45-3
- o fix bug with 'continue' and method 'mif2'
+ • 'abc' implements Approximate Bayesian Computation for pomp
+ models.
-0.45-2
- o new method to coerce 'pfilterd.pomp' objects to data-frames.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_6-_1:
-0.45-1
- o 'profileDesign' can now handle variables of mixed type.
+ • 'pompExample' now has an optional argument, 'envir',
+ determining which environment the pomp object will be loaded
+ into.
-0.44-1
- o New 'mif2' option for 'mif'.
+ • 'logmeanexp' now has an optional argument, 'se', allowing for
+ computation of an approximate standard error.
- o The default behavior for 'mif' and 'pfilter' with respect to filtering failures has been changed.
- Before, the default behavior has been to stop with an error on the first filtering failure ('max.fail=0').
- Now, the default is 'max.fail=Inf', i.e., an error is never triggered.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_5-_8:
- o The implementation of MIF cooling schedules has been changed to make it more general.
- The cooling schedule is now specified by a 'type' and a 'fraction'.
- Currently, supported 'cooling.type's include 'geometric' (the old behavior) and 'hyperbolic', i.e., a 1/(1+n) schedule.
- The 'cooling.fraction' argument specifies the cooling at 50 iterations.
- That is, if s is the intensity of the random-walk perturbation to parameters at the first iteration ('rw.sd'), then the intensity at iteration 50 is s*cooling.fraction.
+ • bug fix in 'gompertz' example.
- o Remove all data()-loadable pomp objects.
- To load the prebuilt example pomp objects from previous versions, use the new 'pompExample' function.
- E.g., instead of 'data(euler.sir)', do 'pompExample("euler.sir")'.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_5-_7:
-0.43-4
- o Clean up tests.
+ • bug fix in 'pmcmc': Metropolis-Hastings ratio was incorrect
+ except for flat priors!
-0.43-3
- o Fix bug in 'pompBuilder' on mac.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_5-_6:
- o Fix bug in 'dmeasure' when log=TRUE. Bug located by R. Reiner.
+ • a fix so that 'pompBuilder' will find 'pomp.h' header file on
+ Windows machines. Thanks to Dave Hayman for finding the
+ problem.
- o Add 'eff.sample.size' and 'cond.logLik' methods for 'pfilterd.pomp' objects.
+ • new 'logmeanexp' function.
-0.43-1
- o Modify 'traj.match.objfun' to allow arbitrary parameters to be passed to the ODE integrator.
+ • some reorganization of the source package structure.
- o Add 'params' argument to 'pomp' so that parameters can be specified at the time the pomp object is created.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_5-_4:
-0.42-6
- o Improve error checking in 'pomp'.
+ • changes in the way 'reulermultinom', 'deulermultinom',
+ 'dot_product' are exported to other packages. Rather than
+ just being exported as linkables, these are now also defined
+ as static inline functions in the 'pomp.h' header.
- o Add support for covariates to 'pompBuilder'.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_5-_3:
- o Add native parameter transformation routines to the demos.
+ • fix bug with 'continue' and method 'mif2'
- o Change the warning behavior in 'lookup_table' so that warnings are not generated unless true extrapolation is performed (i.e., eliminate the warnings at the boundary).
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_5-_2:
- o Some small modifications to the 'pomp.h' header file.
+ • new method to coerce 'pfilterd.pomp' objects to data-frames.
-0.42-4
- o When 'trajectory' calls 'ode', there is a need to preserve information across calls to the vectorfield-evaluating function.
- The code has been modified to do this in a cleaner way.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_5-_1:
-0.42-2
- o Several minor bugs have been fixed.
- See the ChangeLog for details.
+ • 'profileDesign' can now handle variables of mixed type.
-0.42-1
- o An EXPERIMENTAL facility for constructing pomp objects out of native C routines is now included (pompBuilder).
- This facility is being actively developed and future changes may not be backward compatible.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_4-_1:
- o A new facility allowing access to the 'userdata' slot of a pomp object from compiled 'rprocess', 'rmeasure', 'dprocess', 'dmeasure', 'skeleton', and 'partrans' codes is now available.
- Calls to the new C routines 'get_pomp_userdata', 'get_pomp_userdata_int', and 'get_pomp_userdata_double' allow retrieval of these elements.
+ • New 'mif2' option for 'mif'.
- o Some of the data()-loadable examples have been reworked to make use of the above facility.
- The parameterization of these examples has changed.
- These changes are not backward compatible: codes that depend on the data()-loadable examples may be broken.
+ • The default behavior for 'mif' and 'pfilter' with respect to
+ filtering failures has been changed. Before, the default
+ behavior has been to stop with an error on the first
+ filtering failure ('max.fail=0'). Now, the default is
+ 'max.fail=Inf', i.e., an error is never triggered.
-0.41-8
- o A demonstration of 'pompBuilder' has been put into the 'advanced topics' vignette.
+ • The implementation of MIF cooling schedules has been changed
+ to make it more general. The cooling schedule is now
+ specified by a 'type' and a 'fraction'. Currently, supported
+ 'cooling.type's include 'geometric' (the old behavior) and
+ 'hyperbolic', i.e., a 1/(1+n) schedule. The
+ 'cooling.fraction' argument specifies the cooling at 50
+ iterations. That is, if s is the intensity of the
+ random-walk perturbation to parameters at the first iteration
+ ('rw.sd'), then the intensity at iteration 50 is
+ s*cooling.fraction.
-0.41-7
- o A bug in the 'blowflies' example has been fixed.
- Thanks to Greg Minshall for discovering it.
+ • Remove all data()-loadable pomp objects. To load the
+ prebuilt example pomp objects from previous versions, use the
+ new 'pompExample' function. E.g., instead of
+ 'data(euler.sir)', do 'pompExample("euler.sir")'.
-0.41-6
- o The 'gompertz' example parameter transformations have been changed.
- No longer are the names of the parameter vector changed in the transformation.
- This change is not backward-compatible, but only codes using this example are affected.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_3-_4:
- o The 'euler.sir' and 'gillespie.sir' examples have been changed.
- The transmission rate beta(t) is now the arithmetic sum of the seasonality basis functions.
- Before, it was the geometric sum.
- R0 is now given by the arithmetic average of the beta parameters divided by (gamma+mu).
- This change is not backward-compatible, but only codes using these examples are affected.
+ • Clean up tests.
-0.41-5
- o An experimental facility for constructing pomp objects with native C routines is now included.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_3-_3:
-0.41-4
- o The 'blowflies', 'euler.sir', 'gillespie.sir', 'bbs', and 'ricker' data()-loadable examples have been changed to make the parameterization simpler and more natural.
- This change is not backward-compatible, but only codes using this example are affected.
+ • Fix bug in 'pompBuilder' on mac.
-0.41-3
- o In 'trajectory', all vectorfield and map evaluation is now done in C for speed.
- For continuous-time dynamical systems, this gives an approximately 4-fold speedup.
+ • Fix bug in 'dmeasure' when log=TRUE. Bug located by R.
+ Reiner.
- o Demos have been created to show some examples.
+ • Add 'eff.sample.size' and 'cond.logLik' methods for
+ 'pfilterd.pomp' objects.
-0.41-2
- o A segfault bug in 'bbs' example has been fixed.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_3-_1:
- o The posterior medians (not means) are now stored in the 'params' slot of the 'bsmcd.pomp' object.
+ • Modify 'traj.match.objfun' to allow arbitrary parameters to
+ be passed to the ODE integrator.
-0.41-1
- o New arguments in 'mif', 'nlf', 'bsmc', 'pmcmc', 'probe-match', and 'traj-match' allow the estimation to be done on a transformed parameter space.
- When 'transform=TRUE' in these commands ('transform.params=TRUE' for 'nlf'), estimation is performed on the transformed parameter space.
- This is described and demonstrated in the 'intro_to_pomp' vignette.
+ • Add 'params' argument to 'pomp' so that parameters can be
+ specified at the time the pomp object is created.
- o The data()-loadable examples have been re-implemented to make use of the above-mentioned facility.
- Note that this new functionality makes it unnecessary to "un-transform" model parameters within the user-specified 'rprocess', 'dprocess', 'rmeasure', 'dmeasure', 'skeleton', and 'initializer' codes.
- This change is not backward-compatible, but only codes using these data()-loadable example are affected.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_2-_6:
- o The Bayesian sequential Monte Carlo command 'bsmc' now returns not a list but an object of class 'bsmcd.pomp'.
- An experimental 'plot' method for objects of this class now exists.
- Also, the parameter posterior means are now stored in the 'params' slot of the 'bsmcd.pomp' object:
- access them with the 'coef' command as usual.
+ • Improve error checking in 'pomp'.
- o A new example, using data from an influenza outbreak in a British boarding school and an SIR model, has been included.
- Do 'data(bbs)' to load it.
+ • Add support for covariates to 'pompBuilder'.
-0.40-9
- o Setting the new argument 'as.data.frame' to 'TRUE' in 'simulate' and 'trajectory' causes the results to be returned as a data-frame.
+ • Add native parameter transformation routines to the demos.
-0.40-8
- o A new method 'partrans' allows transformation of vectors or matrices of parameters.
- The parameter transformations have been pushed into C for speed.
- It is possible to specify native parameter transformation routines in addition to C functions, but this last facility has not yet been extensively tested.
- A new slot 'has.trans' has been introduced into the 'pomp' class, and the types of slots 'par.trans' and 'par.untrans' have changed.
+ • Change the warning behavior in 'lookup_table' so that
+ warnings are not generated unless true extrapolation is
+ performed (i.e., eliminate the warnings at the boundary).
-0.40-7
- o 'parmat' now gracefully handles the case when 'params' is already a matrix.
+ • Some small modifications to the 'pomp.h' header file.
- o Error in the documentation of 'pfilter' repaired.
- Thanks to Alex Smith for pointing this out.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_2-_4:
- o Improvements in the documentation of the Nicholson blowflies data 'data(blowflies)'.
+ • When 'trajectory' calls 'ode', there is a need to preserve
+ information across calls to the vectorfield-evaluating
+ function. The code has been modified to do this in a cleaner
+ way.
-0.40-6
- o When a pomp object is updated using 'pomp', the 'params' slot will now be copied over (appropriately transformed).
- Before, it was simply dropped.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_2-_2:
- o The 'gillespie.sir' example has been changed to make the reporting rate equal to 'rho'.
- Before, it was fixed at 10%.
+ • Several minor bugs have been fixed. See the ChangeLog for
+ details.
- o A new error-trap has been put into 'probe' and 'probe.match' for the case nsim < nprobes.
- Thanks to Dani Jonas for finding this error.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_2-_1:
-0.40-5
- o More informative error messages when dimension of state space or data space disagree internally.
+ • An EXPERIMENTAL facility for constructing pomp objects out of
+ native C routines is now included (pompBuilder). This
+ facility is being actively developed and future changes may
+ not be backward compatible.
- o The 'weighted' argument to 'mif' and 'continue' is now deprecated in favor of a new argument 'method'.
- The old 'weighted=T' corresponds to 'method="mif"' while the old 'weighted=F' corresponds to 'method="unweighted"'.
+ • A new facility allowing access to the 'userdata' slot of a
+ pomp object from compiled 'rprocess', 'rmeasure', 'dprocess',
+ 'dmeasure', 'skeleton', and 'partrans' codes is now
+ available. Calls to the new C routines 'get_pomp_userdata',
+ 'get_pomp_userdata_int', and 'get_pomp_userdata_double' allow
+ retrieval of these elements.
-0.40-4
- o New functions 'traj.match.objfun' and 'probe.match.objfun' have been added.
- These functions construct functions of one argument suitable for use as objective functions in 'optim'-like optimizers (iincluding 'subplex' and 'sannbox').
- Minimizing these functions solves the trajectory-matching problem and probe-matching problem, respectively.
- This allows the user much greater flexibility in choice of optimization algorithm than is afforded by 'traj.match' and 'probe.match'.
+ • Some of the data()-loadable examples have been reworked to
+ make use of the above facility. The parameterization of
+ these examples has changed. These changes are not backward
+ compatible: codes that depend on the data()-loadable examples
+ may be broken.
- o The 'sannbox' optimizer, which performs simulated annealing with box constraints, is now exported and available for general use.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_1-_8:
-0.40-3
- o The 'bsmc' method has been improved, due to the contributions of Pierre Jacob.
- Specifically, 'bsmc' no longer reports a log-likelihood (which it never actually computed anyway) but a log-evidence.
- The latter computation was supplied by Pierre Jacob.
+ • A demonstration of 'pompBuilder' has been put into the
+ 'advanced topics' vignette.
- o A new helper function, 'exp2geom_rate_correction' has been added to the 'pomp.h' file.
- This function computes the rate r such that if N ~ geometric(prob=1-exp(-r*dt)) and T ~ exponential(rate=R), then E[N*dt] = E[T].
- This is useful in approximating a continuous-time death process by a discrete time (Euler) process.
- In particular, in such a case, T is the waiting time to death in the former and N*dt is the waiting time to death in the latter.
- An Euler binomial or multinomial process with rate r=exp2geom_rate_correction(R,dt) will have the same mean waiting time as the exponential process with rate R.
- Thanks to Sebastien Ballesteros for suggesting this.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_1-_7:
- o A new helper function, 'rgammawn' has been added, with both R and C interfaces.
- This function draws an increment of a Gamma white-noise process with a given intensity.
- Specifically, dw=rgammwn(sigma,dt) is Gamma distributed with mean dt and variance sigma^2*dt.
- In this case, mu*dw/dt is suitable for use as a random rate in an Euler-multinomial process.
- Thanks to Sebastien Ballesteros for suggesting this.
+ • A bug in the 'blowflies' example has been fixed. Thanks to
+ Greg Minshall for discovering it.
-0.40-2
- o A bug to do with computation of the number of steps needed in discrete-time simulation and trajectory computations has been fixed.
- This bug was introduced in version 0.40-1.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_1-_6:
-0.40-1
- o It is now possible for discrete-time determistic skeletons to have a general step-size.
- Before, the stepsize was always forced to be 1.
- The new argument 'skelmap.delta.t' in 'pomp' (default value 1) sets this step-size.
- NB: in implementing this feature, a new slot has been added to the basic 'pomp' class.
- 'pomp' objects created with versions <0.40-1 will not therefore work with this version and must be re-created.
+ • The 'gompertz' example parameter transformations have been
+ changed. No longer are the names of the parameter vector
+ changed in the transformation. This change is not
+ backward-compatible, but only codes using this example are
+ affected.
- o The deterministic skeleton trajectory functions now look for variables named in 'zeronames' and treat these variables as accumulators.
- This brings the behavior of the deterministic skeleton functions into line with 'rprocess'.
- A new section of the "advanced topics" vignette discusses accumulator variables and 'zeronames'.
+ • The 'euler.sir' and 'gillespie.sir' examples have been
+ changed. The transmission rate beta(t) is now the arithmetic
+ sum of the seasonality basis functions. Before, it was the
+ geometric sum. R0 is now given by the arithmetic average of
+ the beta parameters divided by (gamma+mu). This change is
+ not backward-compatible, but only codes using these examples
+ are affected.
- o Include the user manual PDF among the vignettes.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_1-_5:
- o The new function 'parmat' creates a suitable matrix of parameters in one line.
+ • An experimental facility for constructing pomp objects with
+ native C routines is now included.
-0.39-5
- o Bug fix in 'bsmc' that arises when the state space is 1-D.
- Thanks to Arnab Bhattacharya for finding the bug.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_1-_4:
- o Some inconsistencies in the arguments of 'bsmc' have been fixed.
+ • The 'blowflies', 'euler.sir', 'gillespie.sir', 'bbs', and
+ 'ricker' data()-loadable examples have been changed to make
+ the parameterization simpler and more natural. This change
+ is not backward-compatible, but only codes using this example
+ are affected.
-0.39-4
- o Minor corrections to the documentation for 'spect', 'probe', and 'traj.match'.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_1-_3:
- o Fix infelicity in 'traj.match' and 'nlf' that arises when the 'data' slot has no rownames.
- Rownames are not strictly required for the 'data' slot.
+ • In 'trajectory', all vectorfield and map evaluation is now
+ done in C for speed. For continuous-time dynamical systems,
+ this gives an approximately 4-fold speedup.
- o The 'sannbox' algorithm now should work even when the objective function throws a non-finite value.
- The behavior now is to replace non-finite values with a large number.
- This behavior follows that of the 'SANN' method in 'optim.
+ • Demos have been created to show some examples.
-0.39-3
- o The help files for 'pfilter' and 'mif' have been updated to explain how to use a variable number of particles in the particle filtering algorithm.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_1-_2:
- o Inside 'init.state', a check has been added to make sure that the user's initializer function returns a vector of uniform size, as per the algorithms' assumptions.
- Thanks to Micaela Martinez-Bakker for catching this.
+ • A segfault bug in 'bbs' example has been fixed.
- o 'mif' has been modified so as to allow estimation of initial-value parameters alone via fixed-lag smoothing.
+ • The posterior medians (not means) are now stored in the
+ 'params' slot of the 'bsmcd.pomp' object.
-0.39-2
- o When 'po' is a 'pomp'-class object with covariates, 'as.data.frame(po)' and 'as(po,"data.frame")' now contain columns for the covariates.
- The latter are interpolated, if necessary, at the observation times.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_1-_1:
- o Bug fix: when 'pfilter' is called with a single parameter vector supplied in the 'params' argument, these parameters are copied into the 'params' slot of the resulting 'pfilterd.pomp' object.
- Before, this failed when the 'params' slot of the 'pomp' object was empty.
- A similar bug existed in 'traj.match' and has likewise been fixed.
+ • New arguments in 'mif', 'nlf', 'bsmc', 'pmcmc',
+ 'probe-match', and 'traj-match' allow the estimation to be
+ done on a transformed parameter space. When 'transform=TRUE'
+ in these commands ('transform.params=TRUE' for 'nlf'),
+ estimation is performed on the transformed parameter space.
+ This is described and demonstrated in the 'intro_to_pomp'
+ vignette.
- o To eliminate warnings and confusion during package check, 'profile.design' has been replaced by 'profileDesign'.
- For parallelism, 'slice.design' and 'sobol.design' have been replaced by 'sliceDesign' and 'sobolDesign', respectively.
- The older forms are now deprecated and will be removed in a future release.
+ • The data()-loadable examples have been re-implemented to make
+ use of the above-mentioned facility. Note that this new
+ functionality makes it unnecessary to "un-transform" model
+ parameters within the user-specified 'rprocess', 'dprocess',
+ 'rmeasure', 'dmeasure', 'skeleton', and 'initializer' codes.
+ This change is not backward-compatible, but only codes using
+ these data()-loadable example are affected.
-0.39-1
- o New facilities for parameter transformation are provided.
- New optional arguments 'parameter.transform' and 'parameter.inv.transform' to 'pomp' allow the user to specify transformations between natural and internal parameter scalings.
- A new option 'transfom' to 'coef' and 'coef<-' allows the user to get and set parameters on the natural scale.
- See 'pomp?coef' and the "intro_to_pomp" vignette for details and examples.
- Similarly, the 'conv.rec' method now takes an optional 'transform' argument.
+ • The Bayesian sequential Monte Carlo command 'bsmc' now
+ returns not a list but an object of class 'bsmcd.pomp'. An
+ experimental 'plot' method for objects of this class now
+ exists. Also, the parameter posterior means are now stored
+ in the 'params' slot of the 'bsmcd.pomp' object: access them
+ with the 'coef' command as usual.
- o Minor improvements to the documentation.
+ • A new example, using data from an influenza outbreak in a
+ British boarding school and an SIR model, has been included.
+ Do 'data(bbs)' to load it.
-0.38-5
- o 'pfilter' will now give an error if ever a non-finite likelihood (dmeasure value) is returned.
- Before, errors were only generated when dmeasure returned NA.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_0-_9:
- o 'spect' now returns frequencies reflective of the observation times.
- Before, the frequencies were given as fractions of the sampling frequency.
+ • Setting the new argument 'as.data.frame' to 'TRUE' in
+ 'simulate' and 'trajectory' causes the results to be returned
+ as a data-frame.
-0.38-4
- o Improvements to the documentation.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_0-_8:
-0.38-3
- o Clarifications and minor improvements in the help pages.
+ • A new method 'partrans' allows transformation of vectors or
+ matrices of parameters. The parameter transformations have
+ been pushed into C for speed. It is possible to specify
+ native parameter transformation routines in addition to C
+ functions, but this last facility has not yet been
+ extensively tested. A new slot 'has.trans' has been
+ introduced into the 'pomp' class, and the types of slots
+ 'par.trans' and 'par.untrans' have changed.
-0.38-2
- o A new section describing and demonstrating nonlinear forecasting has been added to the "intro to pomp" vignette.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_0-_7:
- o Fixed bug in 'nlf': desire for transient period (nconverge>0) was unrecognized.
+ • 'parmat' now gracefully handles the case when 'params' is
+ already a matrix.
-0.38-1
- o Fixed bug in 'pomp' when 'data' is of class 'pomp': userdata should be preserved.
+ • Error in the documentation of 'pfilter' repaired. Thanks to
+ Alex Smith for pointing this out.
- o Improved discussion of SIR model in "Intro to pomp" vignette.
+ • Improvements in the documentation of the Nicholson blowflies
+ data 'data(blowflies)'.
- o In 'pfilterd.pomp' objects, 'saved.states' and 'saved.params' slots are now length-ntimes lists of arrays.
+_C_h_a_n_g_e_s _i_n _p_o_m_p _v_e_r_s_i_o_n _0._4_0-_6:
- o It is now possible to use variable numbers of particles in 'pfilter'.
- The 'Np' argument may be specified as a single number as before, or now as either a vector of numbers or a function.
+ • When a pomp object is updated using 'pomp', the 'params' slot
+ will now be copied over (appropriately transformed). Before,
+ it was simply dropped.
-0.37-2
- o The "advanced topics" vignette has been much augmented and improved.
+ • The 'gillespie.sir' example has been changed to make the
+ reporting rate equal to 'rho'. Before, it was fixed at 10%.
- o The 'euler.sir' example (load it with 'data(euler.sir)') has a different measurement model: a discretized normal distribution with the same mean and variance as before.
+ • A new error-trap has been put into 'probe' and 'probe.match'
+ for the case nsim < nprobes. Thanks to Dani Jonas for
+ finding this error.
-0.37-1
- o The arguments 'skeleton.map' and 'skeleton.vectorfield' are now deprecated.
[TRUNCATED]
To get the complete diff run:
svnlook diff /svnroot/pomp -r 903
More information about the pomp-commits
mailing list