statistics-resampling

Versión 5.6.0 (2,14 MB) por Andrew Penn
A statistics toolbox with a variety of bootstrap and other resampling tools. (This is most recent and developmental version of the toolbox).
0.0
(0)
30 descargas
Actualizado 2 sep 2024
Ver licencia en GitHub

Citar como

Penn, Andrew Charles. Resampling Methods for Small Samples or Samples with Complex Dependence Structures [Https://Github.com/Gnu-Octave/Statistics-Resampling/]. Zenodo, 2020, doi:10.5281/ZENODO.3992392.

Ver más estilos
Compatibilidad con la versión de MATLAB
Se creó con R2015b
Compatible con cualquier versión desde R2007a
Compatibilidad con las plataformas
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

inst

man

sim

test

No se pueden descargar versiones que utilicen la rama predeterminada de GitHub

Versión Publicado Notas de la versión
5.6.0

This release incorporates Extended (Efron) Information Criterion (EIC), relative likelihood ratios and EIC weights for stepwise regression to `bootlm`. There is also a bug fix that allows `bootbayes` to supports NaN value for PROB input argument.
5.5.18

Various improvements relating to the 'auto' prior option of the 'bayesian' method, particularly for posthoc tests. Also added a warning in the bootbayes function when the PRIOR is set to 0.
5.5.17

Enhancement to the standard error calculations in `bootwild` and the Cohen's d effect sizes in `bootlm` functions when the method is 'wild'.
5.5.16

Fixed bug in `bootstrp` that prevented it from reshaping output (bootstat) correctly when applying vectorized evaluation of bootfun on the data
5.5.15

Fixed syntax error that triggered error when printing output for asymmetric bootstrap-t confidence intervals
5.5.14

Added option to compute bias-corrected confidence intervals with the `bootint` function.
5.5.13

Improved numerical accuracy when solving linear systems in bootlm, bootwild, and bootbayes. Corrected dates that files were modified and updated matlab toolbox and online manual.
5.5.11

Minor update which includes modification to the calculation of influence values (used for BCa intervals) such that they are more consistent with the 'empinf' function in the R 'boot' package
5.5.10

Add check in 'install.m' that issues warning if 'make.m' was not run first. Minor changes to `randtest` and `randtest2` settings that decides when to use exact vs approx permutations. Added extra output argument 'stats' to `bootstrp` function.
5.5.9

Major revamp and improvements to `bootstrp` function. Added new functions `randtest`, `randtest1` and `bootint`. Performance enhancements in `boot`, `bootclust` and `bootknife` functions. Bug fixes in `sampszcalc`. Feature enhancements to `cor`.

5.5.8

Added ability in `bootclust` function to accelerate block (or cluster) bootstrap function evaluations by parallel computing. Added to `bootclust` function a third output argument BOOTDATA - a cell array of data resamples.
5.5.7

Minor changes to documentation and comments.
5.5.6

Added pre-compiled MATLAB mex files for platforms with Apple Silicon processors (boot, smoothmedian), better support for NaN and Inf values (bootlm, bootbayes, bootwild), performance enhancements (bootlm), functionality to calculate standardized para
5.5.5.2

Added support in bootlm function for NaN or Inf (missing values) in categorical predictors. Minor bug fix when executing bootlm with missing values, when the latter causes bootlm to exclude a whole level of a categorical predictor.
5.5.5.0

- Added support for logical (true, false) in GROUP in `bootlm`
- Improved handling of data input (e.g. row vectors and matrices) in `bootlm`
- Added ability to customize posthoc comparisons (with demos added to illustrate too) in `bootlm`
Para consultar o notificar algún problema sobre este complemento de GitHub, visite el repositorio de GitHub.
Para consultar o notificar algún problema sobre este complemento de GitHub, visite el repositorio de GitHub.