ROIstat v3.0 Released!

We are releasing a HUGE update for ROIstat! This release has a number of new features and fixes, including multi-factor ANOVA!

You can download it here:

Download ROIstat!

(ROIstat Changelog)

  • New packages needed
    • In preparation for multi-factor ANOVA, there are a few new packages that will be part of ROIstat's requirements. The code for the new analyses is in the codebase, but is not yet ready for primetime, so you will need to go ahead and get those packages installed:
      • install.packages("EMSaov")
      • install.packages("car")
      • install.packages("nlme")
      • A number of packages have had an update, so you should go ahead and update all of them. You can do this in RStudio by clicking Tools | Check for Package Updates and update whatever needs updating. If you use RGui, you can click on Packages | Update packages... to do the same thing.
  • New Features
    •  Added multi-variable ANOVA
      • Randomized Blocked matched pairs two or more levels
      • Complete block design Latin square
      • Fixed, random, or mixed effects full factorials
      • Nested designs with full factorials
      • Fractional designs, inlcuding properly handling primary (between) and secondary (within) error
      • Properly handling unbalanced designs due to unequal sample sizes or odd-level fractional designs
      • Replicated or unreplicated designs
      • Dispersion tests: ADA, ADM, ADM(n-1)
    • Added a number of useful plots
      • Effect plot that has all significant effects on the same scale to judge the size of the effecct
      • Any significant effect can be plotted
      • Boxplots of all main effects
    • And some other useful tools
      • Parameter estimates from the reduced model (only significant effects)
      • Estimated marginal means close to a stated target (can choose zero or a big number for lower or higher is better)
    • Added multi-variable post-hocs
      • Tukey / Games and Howell, Bonferroni, Holm all pairwise comparisons, equal or unequal variances
  • Bug fixes
    • Fixed minor bug that hid Poisson decimal places widget unless you chose to enter X of interest.
    • Fixed a bug that could prevent getting point information when hovering on the scatterplot
    • Reverted the calculation for binomial confidence intervals. lolcat fixed the bug!
    • Changed the two-sample t-test for unknown but equal variances to Student to reduce confusion
    • Added labels to two-sample tests with data to indicate which data is group 1 or group 2
    • Added a label to show how the D-bar is calculated for the dependent by nature two-sample t-test
    • Changed all ggplots that use density to bw="sj" since it stopped accepting the upper case
    • Took out the last of the aes_string commands
    • Added code to make confidence intervals on regression plots equally across the range of x, instead of where the x's happened to be
    • Removed non-functioning option to select z for a two-sample dependent t-test
    • Fixed bug that didn't allow for 5.15 to be selected when using ANOVA to calculate MSA %EV, %AV, and %RR
    • Added r-squared and adjusted r-squared for Fisher oneway ANOVA
    • Took out blog feeds to prevent the app from hanging if you can't connect to the RSS feed online.
  • Known issues:
    • datamods no longer will load .dat files with only one column - this is a limitation in the packages it uses. A fix is in the works. A workaround is to save that as a .txt file or just cut and paste the data.
    • Long pause once ROIstat loads when using RStudio - this is due to RStudio functions that take 10+ seconds to load. Once they are loaded, it does not affect the app. Consider loading via RGui if this is an annoyance since it loads immediately there.
    • Lin-Mudholkar test fails due to breaking the function when the correlation is 1 (lolcat issue)
    • Reported problem with use data one and two sample tests, object x2 not found (can't replicate)
    • No button on MVP(E) or Mann-Whitney-U test to stop early - may be added in the future
    • The density plot x-axis for the exponential will start at zero even if the minimum is above that


2025 Red Cloud Road
Longmont, CO 80504

Talk to us