The core ƩilveR software package is made up of a number of analysis modules.
Summary statistics that can be calculated include mean, standard deviation, SEM, min, max, median and coefficient of variation.
Analyses include t-test, ANOVA and ANCOVA. Statistical results include ANOVA table, predicted vs. residual plots, predicted means with confidence limits, Planned comparisons and post-hoc tests (Dunnett’s, Tukey, Holm, Hochberg, Hommel, Benjamini-Hochberg and Bonferonni).
Repeated measures analysis using mixed model linear models. Options to model within animal covariance as either compound symmetric, autoregressive or unstructured. Statistical results include overall effects table, predicted vs. residual plots, predicted means with confidence limits, Planned comparisons and post-hoc tests (Tukey, Holm, Hochberg, Hommel, Benjamini-Hochberg and Bonferonni).
This module offers the user the ability to adjust p-values for multiplicity that have been calculated using other statistical software packages. The p-value adjustment procedures available include Holm, Hochberg, Hommel, Benjamini-Hochberg and Bonferonni.
Non-parametric tests include Mann-Whitney (or Wilcoxon) tests, Kruskal-Wallis test, Behrens-Fisher all treatment comparisons and Steel’s all to one test.
Graphical plots that can be created using this module include scatterplots, observed means with standard errors, histograms, box-plots and case profiles plots. Most of these plots can be categorised by up to two factors.
The main purpose of this module is to provide the user with a power and sample size analysis plot. The input can either be an estimate of the mean and variance for the parameter of interest. Alternatively real data can be used with an option for the variance to be adjusted for one factor. The user has the option of considering percentage or actual change from control.
Two Sample t-Test.