LOG-LINEAR MODELING IN PERSONNEL RESEARCH

Log-linear modeling is a discrete multivariate statistical technique that is designed specifically for analyzing data when both the independent and dependent variables are categorical or nominal. The purpose of this paper is to demonstrate the utility of this technique in personnel research. The paper (a) discusses behavioral areas of application, (b) compares log-linear modeling with chi-square and regression analysis, (c) presents the basic principles and hypotheses of log-linear modeling, and (d) shows how the technique is used.     

CHANGING VIEWS FOR PERSONNEL SELECTION RESEARCH

Changes in views of personnel selection research include changing opinions about choosing predictors and criteria, methods of data collection, and methods of evaluating selection procedures. In particular, distinctions are (or can be) made between job-relatedness, inferred in part from validity coefficients based on job-related criteria, and the valid measurement of a trait (attribute), inferred in part from research using construct-related criteria. The major change identified is a reduction in the sanctity with which a single correlation is viewed for either purpose.     

SOME NEW FRONTIERS IN PERSONNEL SELECTION RESEARCH

Current research developments in several areas of personnel selection methodology are reviewed. The areas reviewed represent attempts to develop alternatives to traditional paper-and-pencil methods of test development. These areas include computer-interactive tests in the employment situation, new ways of using life-history information, the use of physical tests in selecting individuals for physically demanding jobs, and the development of job-related medical standards for job assignment.     

A MULTIPLE LEVEL INVESTIGATION OF PERSONNEL RATINGS

A multiple levels of analysis approach was used to assess whether job performance and skill importance ratings were based on individual differences, incumbent/supervisor dyadic agreement, group membership, or functional department. Data were collected as part of a managerial training needs analysis conducted at a large gold and silver mining organization. Participants included 140 incumbent managers and their immediate supervisors, who were embedded in 140 incumbent/supervisor dyads, 39 managerial work groups, and eight departments of the organization. Results from Within and Between Analysis (WABA) suggested that (a) incumbent ratings of both performance and skill importance were characterized by individual differences, (b) supervisory ratings of both performance and skill importance were primarily characterized by between-groups (supervisors) differences, (c) matched incumbent-supervisory performance ratings displayed individual differences, and (d) matched incumbent-supervisory importance ratings displayed dyadic agreement (i.e., between-dyads differences). Practical implications of these results for interpreting these and other types of personnel-related data are discussed.     

ORGANIZATIONAL CHARACTERISTICS AS PREDICTORS OF PERSONNEL PRACTICES

This study investigated the relationship between organizational context characteristics and personnel practices. The following organizational characteristics were hypothesized to influence personnel practices: industry sector, the pursuit of innovation as a competitive strategy, manufacturing technology, and organizational structure. In addition, organizational size and unionization were examined. Results based upon data obtained from 267 organizations provided support for the general hypothesis that personnel practices vary as a function of organizational characteristics. In addition to interorganizational differences in personnel practices, this study illustrates that large intraorganiza-tional differences exist with respect to the practices used for managerial and hourly employees. Implications and future research needs are described.     

AGE DISCRIMINATION AND PERSONNEL PSYCHOLOGY: A REVIEW AND SYNTHESIS OF THE LEGAL LITERATURE WITH IMPLICATIONS FOR FUTURE RESEARCH

One hundred and fifty-two court cases were reviewed to determine the standards set by the courts for establishing a claim of age discrimination under the Age Discrimination in Employment Act, as amended. Fifty-three are discussed. Two major issues were examined in Part 1 of the review: (1) the type and extent of the evidence sufficient to establish a complaint of age discrimination and (2) available defenses against age discrimination complaints. Part 2 discussed employer strategies for averting and/or dealing with discrimination complaints. Also discussed were the research-related implications of the age discrimination case law, as well as the role of professionals in future research.     

MODELING THE EFFECTS OF BANDING IN PERSONNEL SELECTION

Selection outcomes under banding are affected by characteristics of the selection system and the applicant pool. This study examined the effects of eight parameters on the proportions hired from higher- and lower-scoring groups: (a) selection ratio; (b) reliability; (b) fixed vs. sliding bands; (d) top-down vs. random within-band selection; (e) preferential vs. nonpreferential selection; (f) mean differences; (g) standard deviation differences; and (h) proportion of applicants from the lower-scoring group. Simulation results were analyzed in a fully-crossed eight-way ANOVA. Higher-order interactions among selection system and applicant pool characteristics had virtually no effect on selection outcomes; the proportion of the applicant pool from the lower-scoring group accounted for nearly half the variance in out-comes. Other important effects are, in order, the effects of standard deviation differences, mean differences, preferential hiring, and the selection ratio. Applicant pool characteristics have considerably more influence on selection outcomes than do selection system characteristics.