Home

Welcome to the G_String wiki!

G_String is just a tool. A software tool that helps researchers who measure human performance to validate their results. G_String derives its name from the fact that it employs lexical analysis of effect strings to calculate Generalizability coefficients for any valid design. The G_String repository employs Open Source strategy to serve five purposes:

• to give G_String users free and easy access to the current version of the program compatible with the most common desktop operating systems;
• to assist software specialists in easily maintaining or extending the software according to users needs, and the current state of the software industry;
• to help potential users to better understand the theory underlying G_String, and how to use the program;
• to provide a central platform for users and experts to exchange ideas and clarify questions;
• to facilitate the survival of G_String in an ever evolving software eco-system.

G_String is basically a user friendly shell around Robert Brennan's original binary code "urGENOVA".

urGENOVA takes a structured control script prepared by the user, and an appropriately formatted data file. It then performs the required ANOVA calculations, and returns the resulting variance components.

G_String leads the user step-by-step in generating a syntactically correct control script, reads in the data file, executes urGenova and calculates the Generalizability Coefficients from the variance components.

In addition G_String

• can perform D-Studies,
• can extract replication sample sizes automatically from the data file,
• can generate synthetic data files corresponding to urGENOVA control files.