statistics-bootstrap-v3.5.0

• changes to ibootnhst include renaming old name-value pairs 'clusters' and 'strata' to 'nested' and 'block' respectively to reflect the conventional terms used in ANOVA - old names are still recognised for backwards compatibility. The block argument makes the bootstrap semi-parametric since it now automatically centres the data of each block prior to stratified resampling. These changes make it easier to analyse data with randomized block designs and repeated measures designs.

statistics-bootstrap-v3.4.0

• Broadened the application of ibootnhst to dependent data by enabling stratified resampling
• In ibootnhst help, I have added examples of how to use ibootnhst to analyse data acquired from a range of experimental designs, including repeated-measures and split plot designs.
• Changed ibootnhst reporting summary to report p-values in APA style.
• ibootnhst now refers to the test statistic as t rather than q-ratio, and refers to p-values as p-adj. The summary now also includes the degrees of freedom.
• Updated the help of ibootnhst to add a more general description of the method it uses to maintain FWER - single-step maxT procedure

statistics-bootstrap-v3.3.9

• ibootnhst: now truncates p-values at the resolution limit determined by resampling with nboot(1) bootstrap replicates

statistics-bootstrap-v3.3.8

• fixed bug that caused an error when BCa intervals are requested for a function calculated on multivariate data provided as a matrix input argument
• fixed bug that caused the default intervals to be BCa intervals (instead of percentile intervals) when no optional input arguments are provided to ibootci
• added error to prevent BCa intervals being calculated for stratified bootstrap

statistics-bootstrap-v3.3.5

• added dim name value pair and example usage to ibootnhst help
• added automatic calculation of the grand median for matrix input

statistics-bootstrap-v3.3.4

• renamed bootnhst.m to ibootnhst.m to reflect the fact that it performs iterated bootstrap.
• ibootnhst and maxstat: added option to use jacknife, instead of the default bootknife, resampling.
• ibootnhst: updated help information about nboot input argument

statistics-bootstrap-v3.3.2

• jack.m: Fixed bug that meant that caused an error if opt.matflag argument was not specified as an input argument
• bootnhst: Improved estimate of p-value calculations by interpolation
• bootnhst: Made confidence intervals of bootfun reported in stats.group scale when sample sizes are unequal
• bootnhst: Updated missing information in help

statistics-bootstrap-v3.3.1

• updated description info

statistics-bootstrap-v3.3.0

• Added ability to account for hierarchical data structure in bootnhst

statistics-bootstrap-v3.2.4

• bootanovan now resamples residuals (in Matlab only), which extends the variety of models it can support