CRAN release 1.0.4

dsims 1.0.4

Bug Fixes

• Fixed a bug when generating the simulation summary which meant that only the first value of mean.k and n.miss.dists was repeated rather than including all values in the summary tables. Issue #84
• The make.simulation function now throws an error if the P2 ER variance estimator is used with line transects designs (rather than after the simulation has completed). Issue #61

dsims-1.0.3-R4.3.1

This is dsims 1.0.3 built under R version 4.3.1

dsims 1.0.3

Bug Fixes

• Simulations were crashing if there were zero detections - now fixed and warnings displayed instead. Issue #77
• Errors were also occuring when there were no individuals generated in a stratum, now fixed. Issue #80
• Detections are no longer permitted across stratum boundaries - this was causing errors due to NA area values in the data. This is inline with expected protocols on surveys. Issue #81
• Remove dependence on sp and rgeos. Issue #42

dsims 1.0.2

This is the version of dsims shipped with Distance 7.5 release 2.

dsims1.0.1

This is the version of the dsims package which was released with Distance 7.5 release 1

CRAN 1.0.0

Version 1.0.0 as published to CRAN

dsims 1.0.0

New Features

• Reading transects from file - this functionality is primarily envisionged for use from within Distance for Windows

Enhancements

• New routine which will generate covariate values from a zero-truncated Poisson distribution for non integer values.
• There is now no lower limit on the number of detections in simulations as this was introducing bias. There is now a warning system in place. Very low numbers of detections may cause issues fitting. There must be more detections than there are parameters in the model for the model to have a chance of fitting successfully. Note that distance sampling good practice recommends minimum of 60-80 detections for estimating the detection function for line transects and more for points.
• Improved histogram.N.ests function will now plot either a histogram of estimates of individuals or clusters. It also provides the use.max.reps argument so that the plot can be consistent with the option selected for the simulation summary.

Bug Fixes

• Fixed simulations where cluster size was included - there was a formatting change in mrds output tables.
• Added a check for repeat model definitions.
• Add code to deal with equal model criteria values.
• Fixed bug when no simulation repetitions had been successful
• AICc method fixed
• Warning indexes from parallel runs are now fixed

CRAN dsims-0.2.0

dsims 0.2.0

New Features

• Delta selection criteria is now recorded as the difference in informtion criteria between the top 2 best fitting models as determined by the information criteria.]
• The iteration numbers generating warnings or errors are now stored and displayed so user can choose what to do with these results.

Bug Fixes

• Fixed missing RMSE values
• Fix strata re-ordering for cluster size
• Models with -Inf information criteria no longer selected
• Models with dht = NULL are no longer selected
• Models which predict detection values < 1 no longer cause errors and are correctly excluded.
• Detectibility parameters for continuous covariates are now checked and validated.
• Fix situation where all reps are to be excluded due to problematic model fitting.

dsims-0.1.1

The first CRAN release of dsims: Distance Sampling Simulations