Discusses properties of multiple attribute tree (MAT) and inverted file structures; establishes suitability of MAT data structure for bibliographic files using worst-case performance measures; provides arguments to establish MAT average case superiority; and proposes an efficient adaptation of MAT data structure to exploit special features of MAT…

Explains an experiment in text-searching retrieval for cancer questions which developed and used computer procedures (via human simulation) to select search words from medical dictionaries. This study is based on an earlier one in which search words were humanly selected, and the recall results of the two studies are compared. (Author/LRW)

The paper sets the stage for the effective and efficient use of computers in institutional research. The microcomputer and the mainframe computer are contrasted for those researchers who have a choice of where to process data. General computer use, specific microcomputer and mainframe computing guidelines, and an application utilizing both…

Suggests new method of external distribution called tree partitioning that involves use of binary tree to split incoming file into successively smaller partitions for internal sorting. Number of disc accesses during a tree-partitioning sort were calculated in simulation using files extracted from British National Bibliography catalog files. (19…

The results of an examination of computer data formatting and data analysis strategies from two diverse second language projects and their implications for establishing standards are outlined in the form of suggested formatting conventions and analysis procedures. The formatting suggestions address the issues of distinguishing line types,…

Introduces two data distortion methods (Frequency-Imposed Distortion, Frequency-Imposed Probability Distortion) and uses a Monte Carlo study to compare their performance with that of other distortion methods (Point Distortion, Probability Distortion). Indications that data generated by these two methods produce accurate statistics and protect…

Concerns about published comparisons of colleges and universities are organized into a framework to guide further research. A systematic method for addressing specific issues about the guides is presented, and the environment in which the guides are used is examined. Research needed to assure that the guides make a valued contribution and are fair…