Social Science Computer Review

Saltzman, Arthur; Danziger, James N.

doi: 10.1177/089443939301100201pmid: N/A

A disk-based interviewing techmque is used to conduct an extensive survey among members of a large PC user group The survey includes a series of questions on the sources of technical knowledge used by these PC users to gain information about software and hardware. The extent of use and the relative utility of 11 alternative sources of information are assessed. Data on the information source attributes and on the end-user characteristics that might affect the use and utility of the information sources are also analyzed. We conclude that PC magazine articles and friends and colleagues are the most frequently used sources and that these 2 sources and user group members are attributed the greatest utility. In general, whereas accessibility is the most important factor in determining the level of use of an information source, those sources that are less biased and more interpersonal receive the highest utility scores from end users. Keywords personal computers, information utility, information use, user groups, disk-based surveys, opinion leaders, end users.

Anderson, Ronald E.

doi: 10.1177/089443939301100202pmid: N/A

Prison sentencing needs to be comprehensive, adapt to changes over time, and avoid racial, gender, and age disparities. The Structured Sentencing Simulation (sss) addresses these needs through a microsimulation of court and correctional systems, providing parameters to generate the hypothetical impact of changes in sentencing policies. The program design utilizes microsimulation techniques including micro-data input, cell-based submodels, dynamic and static aging, dynamic transition models, discrete time slicing, and disaggregation for output distributions. The quality of the results depends upon the collection and processing of large amounts of data describing an existing population of court sentences, demographic characteristics of those sentenced, cell-based estimates of transition probabilities through the criminal justice system, and global parameter estimates of overall system characteristics. The program output includes 5- and 10-year projections of prison, jail, residential treatment, and community service populations In the output from the model all population counts are broken down by sex, race, age, and other demographic variables enabling policy analysts to momtor the extent to which inmate populations are likely to be free of sentencing disparities The program has been implemented in several state sentencing studies. Aspects of the system have implications for simulations in other social contexts.

deB. Mills, William

doi: 10.1177/089443939301100203pmid: N/A

Computer scientists studying the automation of analytical techniques based on human cognitive processes have in recent years developed several innovative methodologies well suited to social science research. Rule-based analytical tools, databases that return information that is "similar" to that requested, inductive classification of examples, and self-sorting bibliographies are among the potential new tools that could greatly expand the analytical powers of social science researchers. Unfortunately, most social science graduates still remam largely unaware of their potential. This article describes software designed to introduce these methods and show how they can be applied to social science problems.1

Stolzenberg, Lisa; D'Alessio, Stewart J.

doi: 10.1177/089443939301100204pmid: N/A

The statistical analysis of data with missing information occurs with great frequency in quantitative research. Although an enormous amount of literature has been produced on this subject, most of it assumes a strong background in statistics. In this paper we use SPSS/PC+ 4.0 to illustrate seven statistical procedures commonly employed by researchers to deal with missing data. We also assess how the use of a particular technique impacts findings in a multivariate regression analysis. Our results show that parameter estimates differ depending on which missing-data procedure is selected for use in an analysis. The implications of these findings are discussed. Keywords: Missing data, SPSS/PC+, incomplete data, missing observations.

Brookshire, Robert G.

doi: 10.1177/089443939301100205pmid: N/A

For most social scientists, data come m a rectangular form similar to a spreadsheet, where columns represent variables and rows are observations. For a few years now, however, a more complex view of data has been evolving in the fields of computer science and management information systems. The purposes of this paper are to introduce this relational view of data to social scientists and to argue that this way of looking at data can be much more powerful than the traditional view. The first part of the paper introduces the terminology and concepts of the relational model. This is followed by a discussion of relational operators, normalization, and the entity-relationship diagram—a technique used to visualize a relational database. The paper then illustrates these concepts with crime and justice data from the Bureau of Justice Statistics. Keywords: database, data management, relational database.

doi: 10.1177/089443939301100206pmid: N/A

Garson, G. David

doi: 10.1177/089443939301100207pmid: N/A

Call for contributions and reviewers: the Social Science ComputerReview welcomes submission of articles, reports, communications, news items, and software and book reviews. Please contact the appropriate associate editor listed on the inside back cover, or write to the editor, G. David Garson, NCSU Box 8101, Raleigh, NC 27695; 919-515-3067. Regarding book reviews, contact the book review editor, Carl Grafton, Department of Government, Auburn University at Montgomery, Montgomery, AL 36193; 205-277-4685. Note: All products discussed in this section are for MS-DOS computers except where otherwise noted, such as for Macintosh stations or products requiring Windows or OS/2.

doi: 10.1177/089443939301100208pmid: N/A

doi: 10.1177/089443939301100209pmid: N/A

Social Statistics Using MicroCase is an instructional package for undergraduate-level social statistics courses. The text, a 331-page hardback written by sociologist William Fox, is integrated with a student version of the MicroCase software (a menu-driven statistical analysis, mapping, and graphics system). Also included : a workbook with exercises that coincide with the text's chapters, and two 81-variable data files, one comprising variables drawn from the 1990 General Social Survey and the other containing an eclectic assortment variables of the census type for the 50 states. Although higher priced than the $39.95 sPss/pc + Studentware Plus, Social Statistics Using MicroCase offers user-friendly advantages but has the disadvantage of not allowing keyboard data entry or imported data files.

doi: 10.1177/089443939301100210pmid: N/A

Mathematica is not a statistical package. Rather it is the development environment of choice for developing math-based models for financial analysis, economics, management science, data graphics, and similar purposes. Mathematica implements almost a thousand mathematical functions and supports symbolic and graphical computations as well as numerical and is an ideal scientific visualization tool. Mathematica has a built-in programming language and comes with packages for statistics, calculus, linear algebra, geometry, number theory, and other operations. It also interfaces to C and FORTRAN code, MathLink communication, and Notebook interactive documents; and it supports animated graphics, sound, and PostScript output. In summary, Mathematica is a system for representing knowledge in mathematical fields.