Global Dictionary

The Global Dictionary is a workspace-wide repository of parameters that can be accessed and changed from within each node (the Statistica Visual Basic script that defines the data cleaning and filtering node, or the analysis node; see also, How To Write .svx Scripts For Data Miner).  

For example, the General Classifier (Trees and Clusters) or General Modeler and Multivariate Explorer commands display data mining projects for analyzing classification or regression-type problems with sophisticated options for competitive evaluation of models (Voting and Bagging) for deployment. This requires Statistica to evaluate and compare the predictions and predicted classifications from different nodes which each may apply completely different types of models. Each node in such projects publishes results in the global dictionary where they can be accessed for competitive evaluation of models by other nodes.

In general, the global dictionary can be used by advanced designers of dedicated custom project workspaces to create sophisticated projects where different nodes can talk to each other without having to be connected to each other. For example, for quality control applications, a dedicated project might contain in the global dictionary all quality control specifications for all variables that might be used. In this manner, all the user would have to do is to insert analysis (charting) nodes that would automatically create results specifically adjusted for the selected variables (adjusted according to the settings in the global dictionary).

To fully appreciate the power and flexibility afforded by this architecture, and the ability to define parameters that apply to all nodes in the project, review How To Write .SVX Scripts for Data Miner.

See also, Data Mining Definition, Data Mining with Statistica Data Miner, Structure and User Interface of Statistica Data Miner, Statistica Data Miner Summary, and Getting Started with Statistica Data Miner.