Macs in Chemistry

Insanely Great Science

Regress+2.7.1

 

The free univariate data modeling package Regress+ has been updated to version 2.7.1.

Regress+ offers:-

  • Plain textfile input
    • Equations, with or without uncertainties (weights)
    • Distributions, continuous or discrete data
    • Discrete data grouped or ungrouped
  • Datasets up to 4,294,967,295 points (minimum 7)
  • Up to 10 parameters
  • User-selected optimization criterion (where appropriate)
    • Least squares
    • Minimum average abs(residual)
    • Maximum likelihood
    • Minimum K-S statistic
    • Minimum chi-square statistic
  • Full, dated Report (textfile)
  • Robust goodness-of-fit testing for distributions
    • Tunable precision
  • [Optional] State-of-the-art (BCa) central confidence intervals (90, 95 and 99 percent)
    • Tunable precision
  • High-quality (PDF, PNG) plots with one keystroke!
    • X/Y plot, with or without error bars
    • PDF plot
    • CDF plot
    • Probability plot for goodness-of-fit (see above)
    • [Optional] Logarithmic axes (when appropriate)
    • Editable axis labels
    • Automatic tick marks/labels (see above)
  • [Optional] Predictions for unobserved values or percentiles
    • With confidence intervals if desired
  • [Optional] Constant parameter(s)
  • 21 Built-in Equations
    • Plus user-defined model
    • [Optional] Test residuals for systematic error
    • [Optional] List data with fitted estimates and residuals
    • [Optional] Simulated-annealing mode for initial parameter estimates
  • 59 Built-in Distributions
    • 9 continuous, symmetric
    • 27 continuous, skewed
    • 11 continuous mixtures
    • 6 discrete
    • 6 discrete mixtures
    • [Optional] Creation of synthetic samples
  • No hidden assumptions anywhere
    • No approximations, apart from those common to sampling and bootstrapping generally
    • No data transformations of any kind
  • Extensive documentation

There is comprehensive listing of Mac OSX data analysis packages here.

blog comments powered by Disqus