Methods for the Behavioral, Educational, and Social Sciences (MBESS) is an R Package that provides various methods that are especially applicable to the behavioral, educational, and social sciences. For those not familiar with R, R is a powerful program for statistical computing and graphics. R is freely available under the Free Software Foundation's GNU General Public License and is an extremely valuable tool for research. You can find out about the world wide R project here: http://www.r-project.org. MBESS also has its own listserv for help and discussion (join the MBESS listserv).
The Goal of MBESS
The goal of MBESS is to provide substantive and quantitative researchers, especially in the behavioral, educational, and social sciences, with a package that contains useful functions for the unique types of quantitative techniques used in these domains. Although there are many R packages developed with specific areas of inquiry in mind, few packages exist that are devoted to the idiosyncratic techniques used within the behavioral, educational, and social sciences sciences (Of course, many of these techniques also extend to other domains.). One of the long term goals of MBESS is to contain a relatively complete set of functions to compute confidence intervals for various effect sizes (especially those based on noncentral distributions). Another long term goal is to contain a relatively complete set of functions to compute necessary sample size from the Power Analytic and the Accuracy in Parameter Estimation approach.
Contribute
Anyone is free to contribute to this project. Contributions can be as simple as submitting ideas for functions that you would like to see included in the MBESS package (feel free to email me with any ideas) or by submitting functions (hopefully with documentation) that can be included in the package (of course credit will be given for individuals who contribute code).
Licensing Information
The MBESS package is Open Source software that follows the guidelines set forth by the Free Software Foundation's GNU General Public License. Thus, the MBESS software (i.e., code) is freely available to anyone and can be freely modified by anyone (although, if the MBESS package is modified its name must be changed).
Status of MBESS
The first public release version of MBESS was released May 6, 2006. The MBESS source code, binarys, and help files are available on the Comprehensive R Archival Network's MBESS page. The easiest way to get MBESS is actually to use the "install package(s)" facility within R.
Selected Functions Contained within MBESS
Many of the functions contained within MBESSare related to my methodological work in one way or another. Below is a listing of some of the function names (in italics) and a very brief description of what they do. After MBESS in installed and loaded into the R session (using "library(MBESS)" from within R), a question mark followed by the function name (?function.name) will return the help page for particular function. As can be seen, many of the functions relate to sample size planning (from the accuracy in parameter estimation and the power analytic approach) and confidence intervals for effect sizes.
Expected.R2: Expected value of the squared multiple correlation coefficient given the number of predictors, sample size, and the population squared multiple correlation coefficient.
F.and.R2.Noncentral.Conversion: Conversion function when going from the F-statistic to the squared multiple correlation coefficient.
Gardner.LD: Data set of Gardner's learning data, which was used by L. R Tucker when developing analysis of change techniques.
Variance.R2: Calculates the variance of R2 given the number of predictors, sample size, and the population squared multiple correlation coefficient.
ci.R2: Confidence interval for the squared multiple correlation coefficient (R2).
ci.cv: Confidence interval for the coefficient of variation.
ci.reg.coef: Confidence intervals for standardized and unstandardized regression coefficients.
ci.smd: Confidence intervals for the standardized mean difference (also known as Cohen's d).
ci.smd.c: Confidence intervals for the standardized mean difference using the control group standard deviation in the denominator (Glass's g).
conf.limits.ncf: Confidence interval for noncentral F parameters.
conf.limits.nct: Confidence interval for noncentral t parameters.
conf.limits.nc.chisq: Confidence intervals for noncentral chi-square parameters.
signal.to.noise.R2: Several ways to estimate the population signal to noise ratio, P2/(1-P2) (where P is the population multiple correlation coefficient); the "obvious method" is biased.
smd: Standardized mean difference (also known as Cohen's d or Hedges g').
smd.c: Standardized mean difference using the control group standard deviation in the denominator (Glass's g).
ss.aipe.R2: Sample size for the goal of AIPE for the squared multiple correlation coefficient.
ss.aipe.R2.sensitivity: Sensitivity analysis when planning sample size with the goal of AIPE for the squared multiple correlation coefficient.
ss.aipe.reg.coef: Sample size given the goal of AIPE for standardized and unstandardized regression coefficients.
ss.aipe.reg.coef.sensitivity: Sensitivity analysis when planning sample size given the goal of AIPE for standardized and unstandardized regression coefficients.
ss.aipe.smd: Sample size planning given the goal of AIPE for the standardized mean difference.
ss.aipe.smd.sensitivity: Sensitivity analysis when planning sample size given the goal of AIPE for the standardized mean difference.
ss.power.R2: Sample size planning for statistical power for the squared multiple correlation coefficient.
ss.power.reg.coef: Sample size planning for statistical power for standardized and unstandardized regression coefficients.
t.and.smd.conversion: Conversion function when going from a t-statistic to the standardized mean difference.